dataset
stringclasses 4
values | id
stringlengths 5
13
| messages
listlengths 2
6
|
|---|---|---|
cot
|
cot_85562
|
[
{
"content": "Q: Given the sentence \"A little girl is dressed in a pink ballerina costume.\" is it true that \"A girl is dressed as a monkey.\"?\nA: One can be either dressed in a ballerina costume or as a monkey.\nThe answer is no.\n\nQ: Given the sentence \"A man pointing across a table at a woman.\" can we conclude that \"A man points accusingly at a woman.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: The man could be pointing at something interesting for the woman to look at and is not pointing accusingly at her.\nThe answer is it is not possible to tell.\n\nQ: If \"Three men talking by the beach.\" does that mean that \"Three men argue over the direction of their baseball team.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: The three men could have been talking about football instead of arguing over the direction of their baseball team.\nThe answer is it is not possible to tell.\n\nQ: Premise: \"At a beach a ball is in the air while a man in a red long-sleeved shirt and dark pants is lunging forward.\"\nHypothesis: \"A man in red is lunging foward while a beach ball is in the air.\"\nDo we know that the hypothesis entailed by the premise?\nA:",
"role": "user"
},
{
"content": "A man in a red long-sleeved shirt is still a man in red.\nThe answer is yes.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_75538
|
[
{
"content": "You will be given a definition of a task first, then some input of the task.\nIn this task, you're given a fill-in-the-blank question that contains two object names. Additionally, you're given one answer which is one of the objects present in the question. In this task, you need to minimally change the given question so that the answer flips to another object in the question. Remember the question has to be about both objects which are related but different; for example, \"trophy\" and \"suitcase\". This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"small\" to \"big\"). You should not change any content in the given question beyond a word or two, i.e., the trigger word/phrase. The expected answer to your question must not be associated with just the trigger word; instead, it should depend on the context present in the question. The expected answer should not be ambiguous. For your question, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. In your generated question, retain the object names from the input question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. The two objects should be used ONCE in your question. Here is a list of attributes and associated contrastive words that may help write contrastive trigger words. Note that contrastive trigger words help in flipping the label.\n| Attribute | triggerword | contrastive triggerword | \n| age | old | new | \n| altitude | low | high |\n| area | small | vast | \n| brightness | dark | light | \n| clarity | obscure | clear | \n| cleanness | dirty | clean | \n| complexity | simple | complex | \n| cost | cheap | expensive |\n| density | sparse | dense |\n| depth | shallow | deep |\n| distance | near | far | \n| electric conductivity | low | high |\n| flexibility | rigid | flexible |\n| granularity | fine | coarse | \n| hardness | soft | hard | \n| length | short | long | \n| magnitude | small | large | \n| mass | small | large | \n| odor | weak | strong | \n| pressure | low | high | \n| resistance | low | high | \n| shape | round | sharp |\n| shape | flat | spiky |\n| size | small | large | \n| sound | quiet | loud | \n| sound pitch | low | high | \n| speed | slow | fast | \n| stability | unstable | stable | \n| strength | weak | strong | \n| temperature | low | high | \n| texture | smooth | rough | \n| thermal conductivity | low | high |\n| thickness | thin | thick | \n| volume | small | large |\n| weight | light | heavy | \n| width | narrow | wide | \n| location | in | out |\n| location | up | down |\n| location | above | below |\n| location | on | off |\n| location | to | from |\n\n\nContext Word: shrink. \nQuestion: No matter how much we tried to shrink it, the stick could not fit through the hole, as the _ was too wide. \nAnswer: stick.\nOutput:",
"role": "user"
},
{
"content": "No matter how much we tried to shrink it, the stick could not fit through the hole, as the _ was too narrow.",
"role": "assistant"
}
] |
cot
|
cot_55365
|
[
{
"content": "QUESTION: Given the sentence \"A very large bird flying over water.\" is it true that \"The bird is large.\"?\n\nLet's solve it slowly: The bird is large no matter the action of the bird.\nThe answer is yes.\n[QUESTION] If \"Large stuffed bears hang above a carnival game.\" does that mean that \"The carnival game offers little ceramic giraffes as prizes.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nThe carnival game would not have large stuffed bears hanging above it if the prizes are ceramic giraffes.\nThe answer is no.\nQ: Test for natural language inference.\nPremise: \"A man in the city outside a building standing on the steps.\"\nHypothesis: \"A man outside.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: The man is in the city so it implies that he is outside.\nThe answer is yes.\nQUESTION: If \"The girl in the white dress is going down the blue slide.\" does that mean that \"The girl in the white dress is going down the blue slide.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: Both examples are a girl in a white dress going down the slide.\nThe answer is yes.\n[QUESTION] If \"A girl sitting down drinking water surrounded by girls helping her feeling better.\" does that mean that \"A girl is drinking water while riding a bike.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nThe girl can't be riding a bike if other girls are helping her feel better.\nThe answer is no.\nQ: Given the sentence \"Three females talking in front of a sallie mae banner.\" is it true that \"Two old men discuss the days weather angrily.\"?\nA:",
"role": "user"
},
{
"content": "The group cannot consist of both three and two people. The people cannot be both females and men.\nThe answer is no.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_77521
|
[
{
"content": "Definition: In this task, you're given a fill-in-the-blank question that contains two object names. Additionally, you're given one answer which is one of the objects present in the question. In this task, you need to minimally change the given question so that the answer flips to another object in the question. Remember the question has to be about both objects which are related but different; for example, \"trophy\" and \"suitcase\". This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"small\" to \"big\"). You should not change any content in the given question beyond a word or two, i.e., the trigger word/phrase. The expected answer to your question must not be associated with just the trigger word; instead, it should depend on the context present in the question. The expected answer should not be ambiguous. For your question, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. In your generated question, retain the object names from the input question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. The two objects should be used ONCE in your question. Here is a list of attributes and associated contrastive words that may help write contrastive trigger words. Note that contrastive trigger words help in flipping the label.\n| Attribute | triggerword | contrastive triggerword | \n| age | old | new | \n| altitude | low | high |\n| area | small | vast | \n| brightness | dark | light | \n| clarity | obscure | clear | \n| cleanness | dirty | clean | \n| complexity | simple | complex | \n| cost | cheap | expensive |\n| density | sparse | dense |\n| depth | shallow | deep |\n| distance | near | far | \n| electric conductivity | low | high |\n| flexibility | rigid | flexible |\n| granularity | fine | coarse | \n| hardness | soft | hard | \n| length | short | long | \n| magnitude | small | large | \n| mass | small | large | \n| odor | weak | strong | \n| pressure | low | high | \n| resistance | low | high | \n| shape | round | sharp |\n| shape | flat | spiky |\n| size | small | large | \n| sound | quiet | loud | \n| sound pitch | low | high | \n| speed | slow | fast | \n| stability | unstable | stable | \n| strength | weak | strong | \n| temperature | low | high | \n| texture | smooth | rough | \n| thermal conductivity | low | high |\n| thickness | thin | thick | \n| volume | small | large |\n| weight | light | heavy | \n| width | narrow | wide | \n| location | in | out |\n| location | up | down |\n| location | above | below |\n| location | on | off |\n| location | to | from |\n\nInput: Context Word: hospital. \nQuestion: John fixed seeing his doctor at the park and no more at the hospital because the _ is always busy. \nAnswer: hospital.\nOutput:",
"role": "user"
},
{
"content": "John fixed seeing his doctor at the park and no more at the hospital because the _ is always quiet.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_72727
|
[
{
"content": "Teacher:In this task, you're given an article and an answer. Your task is to generate the fill-in-the-blank question for this answer based on the given article. The blanks are always at the end of the question, and can be filled with more than one word or phrase.\nTeacher: Now, understand the problem? Solve this instance: Article: Sometimes life makes more sense when you look at it in reverse . That's certainly been true for me. Last Christmas, at 39, I caught a disease which attacked my knees and eyes. At its worst I could hardly walk or see. For months I' d have to crawl across the floor to use the bathroom or get a drink of water when my husband wasn't home. For a while I could only see shapes and colors so I couldn't drive. My parents kept begging me to let them come out to stay with me in Los Angeles, but our apartment is small and I knew there was nothing they could really do to help me. For the excellent health insurance my husband had through his job, I was receiving the best medical care possible. My only problem was that I couldn't drive to my doctors' appointments and I didn't want my husband to keep missing work to drive me. Three days after I explained this to my parents, a check came from them with a note saying this was \"taxi money\". Several months later another check showed up from my brother to help make up our income since I wasn't able to work. It probably goes without saying that I was extremely grateful to have family members who could and would support me during the hard time. In terms of my day-to-day existence, I live in a village within Los Angeles called Brentwood so I was able to walk to the local post office, market, bank, and library. But once there, I had to depend on the kindness of strangers to help me. Los Angeles is a big city, but I lived in a village with a wonderful community of people who were kind and patient. Slowly I became well. Life was good again and I thought I had a clear understanding of the blessings this illness has provided. \n Answer: taught her to drive a car\nStudent:",
"role": "user"
},
{
"content": "When the author's husband was at home, he _ .",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_50201
|
[
{
"content": "input question: Jordan created consumer awareness and positive comments to help the reputation of their new product. Given that the answer to a question is \"cunning\", what is the question????\noutput answer: How would you describe Jordan?\n\n\nRemy went into his friend's room and found some poker cards laying on the ground. Given that the answer to a question is \"enter the room\", what is the question?\n----\nAnswer: What does Remy need to do before this?\n\n\nQ: Alex was working on the motor in the garage for his car. Alex didn't know much about it so he required help on the part. Given that the answer to a question is \"resourceful\", what is the question?\nA: How would you describe Alex?\n\n\nQuestion: Riley walked toward the house and kept their hands loosely at their sides, ready for any sudden movement. Given that the answer to a question is \"be on guard just in case\", what is the question?\nAnswer: What will Riley want to do next?\n\n\n[Q]: Aubrey invited Lee over for a party, but Lee was being obnoxious. Aubrey made Lee go home. Given that the answer to a question is \"apologize to Aubrey\", what is the question?\n****\n[A]: What will Lee want to do next?\n\n\nProblem: Given the question: Robin transmuted the bad outcome into gold after the troll killed her father. Given that the answer to a question is \"lonely, but glad to have gold\", what is the question?\n++++++++++++++++++++++++++++++++\nThe answer is:\n",
"role": "user"
},
{
"content": "How would Robin feel afterwards?",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_83016
|
[
{
"content": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nCraft one correct answer to the question given in input. To make it more interesting, try to use non-stereotypical language if possible. Make sure your correct answer is reasonably long, consistent with the context, and requires common sense (instead of explicit extraction from the context.) In your answer, use as few words as possible from the given context. Use a response that is uncommon/non-stereotypical, so that it is less predictable. To be less repetitive, please vary your language for each question.\n\nContext: I was told, in person over the phone, that my shoes were on their way. They have my money. I have no shoes. \nQuestion: What may happen after the call?\nSolution: I will return the shoes and get back the money.\nWhy? Excellent correct answer: as it presents a non-stereotypical solution involving \"return\".\n\nNew input: Context: Trying to think what has been happening since I last wrote ... we had my mum staying here for 3 weeks , which was fabulous . It 's been 3 yrs since I saw her last and it was so hard to have her leave . We had a great time while she was here - we went fruit picking and nearly made ourselves sick eating blackberries and raspberries , and did lots of day trips . \nQuestion: Why did we go fruit picking ?\nSolution:",
"role": "user"
},
{
"content": "We needed to get some fruit , plus it was bonding time .",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_85948
|
[
{
"content": "In this task, you're given the title of a five-sentence story and the first four sentences. Your job is to write the last sentence of the story to not connect with the rest of the story. Ensure that the generated sentence is contextually relevant to the story.\n\nEx Input:\nTitle: Evan's Clothes. Sentence 1: Evan was looking for something to wear. Sentence 2: He looked in his closet and found a shirt and some jeans. Sentence 3: Evan put on the shirt. Sentence 4: Then, he put on the jeans.\n\nEx Output:\nThe first hurricane has begun to hit the island and she's prepared.\n\n\nEx Input:\nTitle: Red Balloon. Sentence 1: John was at work. Sentence 2: He wanted more customers to come into the store. Sentence 3: He went to Walmart and bought some red balloons. Sentence 4: He then blew up the balloons and tied them up outside.\n\nEx Output:\nThe client continued doing more and more business with the company.\n\n\nEx Input:\nTitle: No Free Speech. Sentence 1: Sandra was discussing a problem on a forum with other posters. Sentence 2: The members were trying to help each other work through the problem. Sentence 3: Misunderstanding, a moderator publicly reprimanded one of the members. Sentence 4: When Sandra objected to the public rebuke, she was banned.\n\nEx Output:\n",
"role": "user"
},
{
"content": "He decided to stay with his dad and missed the trip.\n\n\n",
"role": "assistant"
}
] |
cot
|
cot_73221
|
[
{
"content": "Q: Premise: \"Four women rollerblade.\"\nHypothesis: \"Men are skiing down a steep slope.\"\nDo we know that the hypothesis entailed by the premise?\nA: There must either be four women or a group of men.\nThe answer is no.\nQUESTION: Can we conclude from \"A baby in a cornfield feeding some food to a young child who is kneeling.\" that \"One brother eats food that his younger brother hands him.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\n\nLet's solve it slowly: If you're feeding someone food you wouldn't eats food at the same time.\nThe answer is it is not possible to tell.\n[QUESTION] Given the sentence \"A young child in a green shirt is on a carousel.\" is it true that \"The young child is wearing a blue shirt.\"?\nPerson wearing a green shirt can not be wearing blue shirt at the same time.\nThe answer is no.\nQ: Given the sentence \"A man in glasses and jeans sitting on a doorstep.\" can we conclude that \"The man had pajamas on.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: The man can not have pajamas on if hes in jeans.\nThe answer is no.\nQUESTION: If \"A few people sitting on a pier looking at a lake.\" does that mean that \"A group of people are watching the sun go down over the lake.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: A group can be doing other activities at a lake besides watching the sun go down.\nThe answer is it is not possible to tell.\nQUESTION: If \"Dark colored mercury car parked in front of pnc bank.\" does that mean that \"The mercury was a getaway car for a bank robbery.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly:",
"role": "user"
},
{
"content": "Not all cars that are parked in front of a bank are involved in a bank robbery as a getaway car or any other role.\nThe answer is it is not possible to tell.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_89148
|
[
{
"content": "TASK DEFINITION: You are given a statement written in Panjabi. Choose the most logical word from the given 4 options which can be used to replace the <MASK> token in the statement. Output the word from the correct option .\nPROBLEM: Statement: 1932 ਦੀਆਂ ਓਲੰਪਿਕ ਖੇਡਾਂ ਲਾਸ ਏਂਜਲਸ ਵਿੱਚ ਹੋਈਆਂ ਸਨ। ਸ਼ੁਰੂਆਤ ਵਿੱਚ ਭਾਰਤ ਨੇ <MASK> ਨੂੰ 11-1 ਨਾਲ ਹਰਾਇਆ। ਦੂਜਾ ਮੁਕਾਬਲਾ ਭਾਰਤ ਨੇ ਅਮਰੀਕਾ ਨੂੰ ਹਰਾ ਕੇ 24-1 ਨਾਲ ਜਿੱਤਿਆ। ਇਸ ਮੈਚ ਵਿੱਚ ਧਿਆਨ ਚੰਦ ਅਤੇ ਉਸ ਦੇ ਭਰਾ ਰੂਪ ਸਿੰਘ ਨੇ 8-8 ਗੋਲ ਕੀਤੇ ਸਨ। ਇਸ ਤਰ੍ਹਾਂ ਦੂਜੀ ਵਾਰ ਭਾਰਤ ਓਲੰਪਿਕ ਚੈਂਪੀਅਨ ਬਣਿਆ।\n\n Option A: ਜਰਮਨੀ\n\n Option B: ਨਿਊਜ਼ੀਲੈਂਡ\n\n Option C: ਜਪਾਨ\n\n Option D: ਬੈਲਜੀਅਮ\n\nSOLUTION: ਜਪਾਨ\n\nPROBLEM: Statement: ਦਿੱਵਿਆ ਭਾਰਤ ਦਾ ਜਨਮ <MASK>, ਭਾਰਤ, ਵਿਚ ਬੀਮਾ ਆਫ਼ਿਸਰ ਤੇ ਉਸਦੀ ਪਤਨੀ, ਮੀਤਾ ਭਾਰਤੀ ਦੇ ਘਰ ਹੋਇਆ। ਦਿੱਵਿਆ ਦਾ ਇੱਕ ਛੋਟਾ ਭਰਾ ਕੁਨਾਲ ਸੀ ਅਤੇ ਦੋ ਭਰਾ ਹੋਰ ਸਨ ਜੋ ਉਸਦੇ ਪਿਤਾ ਦੇ ਪਹਿਲੇ ਵਿਆਹ ਤੋਂ ਭਾਰਤੀ ਦੇ ਦੋ ਹੋਰ ਭਰਾ ਸਨ। ਇਸਨੂੰ ਹਿੰਦੀ, ਅੰਗਰੇਜ਼ੀ ਅਤੇ ਮਰਾਠੀ ਭਾਸ਼ਾਵਾਂ ਦਾ ਪੂਰਾ ਗਿਆਨ ਸੀ। ਦਿਵਿਆ ਭਾਰਤੀ ਦਾ ਬਚਪਨ ਮੁੰਬਈ ਵਿੱਚ ਬੀਤਿਆ। ਉਸ ਨੇ ਆਪਣੀ ਮੁਢਲੀ ਪੜ੍ਹਾਈ ਮਾਨੇਕਜੀ ਕੂਪਰ ਹਾਈ ਸਕੂਲ ਜੁਹੂ, ਮੁੰਬਈ ਤੋਂ ਕੀਤੀ। ਉਸ ਨੇ 9ਵੀਂ ਕਲਾਸ ਹੀ ਪਾਸ ਕੀਤੀ ਸੀ ਕਿ ਉਹ ਫ਼ਿਲਮਾਂ ਵਿੱਚ ਆ ਗਈ ਤੇ ਉਸ ਦੀ ਪੜ੍ਹਾਈ ਵਿਚਾਲੇ ਹੀ ਰਹਿ ਗਈ।\n\n Option A: ਬੰਬਈ\n\n Option B: ਹੁਸੈਨਪੁਰ\n\n Option C: ਮੁੰਬਈ\n\n Option D: ਦੀਵਾਨਾ\n\nSOLUTION: ਬੰਬਈ\n\nPROBLEM: Statement: ਸੋਕੇ ਦੇ ਕਾਰਨ ਵਾਂਗ ਲੰਗ ਆਪਣੇ <MASK> ਨਾਲ ਪਿੰਡ ਛੱਡ ਕੇ ਦੱਖਣ ਵੱਲ ਚਲਿਆ ਜਾਂਦਾ ਹੈੈ। ਉੱਥੇ ਜਾ ਕੇ ਉਹ ਰਿਕਸ਼ਾ ਚਲਾਉਣ ਲੱਗ ਜਾਂਦਾ ਹੈ। ਵਾਂਗ ਲੰਗ ਦਾ ਪਿਓ ਉੱਥੇ ਭੀਖ ਮੰਗਦਾ ਹੈ, ਪਰ ਉਹ ਕੁਝ ਵੀ ਨਹੀਂ ਕਮਾ ਪਾਉਂਦਾ ਅਤੇ ਉਸ ਦੇ ਬੱਚੇ ਤੇ ਉਸ ਦੀ ਪਤਨੀ ਵੀ ਭੀਖ ਮੰਗਦੇ ਹਨ। ਇੱਕ ਦਿਨ ਸੋਕਾ ਪੀੜਿਤ ਲੋਕ ਇੱਕ ਸ਼ਾਹੂਕਾਰ ਦੀ ਹਵੇਲੀ ਵਿੱਚ ਹਮਲਾ ਕਰ ਦਿੰਦੇ ਹਨ। ਉਸ ਹਵੇਲੀ ਵਿਚੋਂ ਵਾਂਗ ਲੰਗ ਦੇ ਹੱਥ ਸੋਨੇ ਦੀ ਪੋਟਲੀ ਲੱਗ ਜਾਂਦੀ ਹੈ ਅਤੇ ਓ ਲੇਨ ਨੂੰ ਹੀਰੇ ਮਿਲਦੇ ਹਨ।\n\n Option A: ਜਾਪਾਨ\n\n Option B: ਅਮਰੀਕਾ\n\n Option C: ਸਰਬੀਆਈ\n\n Option D: ਪਰਿਵਾਰ\n\nSOLUTION:",
"role": "user"
},
{
"content": "ਪਰਿਵਾਰ\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_87451
|
[
{
"content": "instruction:\nIn this task, you're given the title and three arbitrary sentences out of a five-sentence story. You are also given three additional sentence options, a, b, and c, that may or may not belong to the story. Your job is to pick the two options that seamlessly connect with the rest of the story; note that the selected choices may fit into the story at any point. Indicate your selected choices in order, i.e., as 'ab'/'bc'/'ac' and not as 'ba'/'ca'/'cb'. If options are equally plausible, pick the ones that make more sense.\nquestion:\nTitle: Kate was at her mom's house out of town. But the couch was soft, and sunk too low. It was the worst sleep of her life. Choices: a. She decided she would sleep on the couch. b. She tossed and turned all night. c. Tom threw a party as a result.\nanswer:\nab\n\n\nquestion:\nTitle: The congregation was sad, but the pastor told them it was a blessing. They were able to have a larger building constructed. This was helpful since the congregation was continuing to grow. Choices: a. When she was done she felt so relieved. b. A tornado hit one church in town and destroyed it. c. The church had plenty of insurance coverage.\nanswer:\nbc\n\n\nquestion:\nTitle: David stepped up to bat. The pitcher threw a curveball and David missed. David's team celebrated by dumping water all over David and cheering. Choices: a. The teams were tied and this was the last inning. b. On the second pitch David hit a homerun. c. Travis was happy that he had built such a sturdy shelf!\nanswer:\n",
"role": "user"
},
{
"content": "ab\n\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_91483
|
[
{
"content": "In this task, you are given inputs i,j, and A, where i and j are integers and A is a list. You need to return the sum of all the numerical elements in the list A between the positions i and j (including positions i and j). Return 0 if no numerical element is present in the list between the given ranges. i and j will be non-negative, and will always have a value less than the length of A. i will always be less than j.\n\nEx Input:\n10, 12, ['465', 'V', '3045', 'M', 'Z', '4053', '9621', '6909', '3161', 'M', '6675', '2313', 'v', 'g', 'a', 'x', '9347', 'd', 'x', '4309', '7231', '9745', 'F', '8863', '4667', '2089', 'x']\n\nEx Output:\n8988\n\n\nEx Input:\n1, 3, ['p', '5665', '3001']\n\nEx Output:\n8666\n\n\nEx Input:\n2, 12, ['5857', '6775', '9419', '9705', 'n', '6525', '9823', '4123', 'Z', '6231', 'B', 'D', 'j', 'W', '1317', 'z', '9659', '4861', 'j', 'v']\n\nEx Output:\n",
"role": "user"
},
{
"content": "52601\n\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_89399
|
[
{
"content": "In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to collate all the alphabetical elements at the start of the list followed by all the numerical elements of the list. Maintain the order in which the alphabetical elements appear in the given input list, and do the same for the numerical elements.\n\nEx Input:\n['e', '3865', 'E', '3945', '6479', 'X', '565', 'C', '9113', 'i', '8355', '7467', 'X', '6577', 'P', 'Q', '4039', 'N', '7993', 'x', 'u', '7455', 'w', 'P', 'q', 'h', 'p', 's', '2323', 'N', '1171', 'h', '2049', 'n', 't', 'A', '7143']\n\nEx Output:\ne, E, X, C, i, X, P, Q, N, x, u, w, P, q, h, p, s, N, h, n, t, A, 3865, 3945, 6479, 565, 9113, 8355, 7467, 6577, 4039, 7993, 7455, 2323, 1171, 2049, 7143\n\n\nEx Input:\n['G', '9601', '531', 'k', '1475', 'd', 'z', '3605', '5159', 'V', '8553', '4219', 'Q', '5021', '971', 'X', '1511', 'h', '6951', '7755', '7171', 'N', 'e', '8049', '6269', 'S']\n\nEx Output:\nG, k, d, z, V, Q, X, h, N, e, S, 9601, 531, 1475, 3605, 5159, 8553, 4219, 5021, 971, 1511, 6951, 7755, 7171, 8049, 6269\n\n\nEx Input:\n['4851', 'X']\n\nEx Output:\n",
"role": "user"
},
{
"content": "X, 4851\n\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_55474
|
[
{
"content": "[Q]: Sasha expected Riley to attack once, but was not expecting them to press forward with a second swing. Given that the answer to a question is \"not used to fighting\", what is the question?\n****\n[A]: How would you describe Sasha?\n\n\ninput: Please answer the following: Jordan found Jan's slick backpack underneath her bed late at night. Given that the answer to a question is \"say thank you\", what is the question?\n++++++++++\noutput: What will Jan want to do next?\n\n\nPlease answer this: Remy did something he shouldn't have done. Remy needed to tell Austin the truth. Given that the answer to a question is \"an honest person\", what is the question?\n++++++++\nAnswer: How would you describe Remy?\n\n\nProblem: Jordan was in the back of the line when he spotted Austin. Jordan called out Austin's name from the back. Given that the answer to a question is \"happy\", what is the question?\n\nA: How would Austin feel as a result?\n\n\nProblem: Given the question: As Kendall's attorney, Lee got everything needed to settle Kendall's affairs. Given that the answer to a question is \"sign the document\", what is the question?\n++++++++++++++++++++++++++++++++\nThe answer is:\nWhat will Kendall want to do next?\n\n\nProblem: Austin begged and begged for a new puppy from their parents. Given that the answer to a question is \"annoyed\", what is the question?\n\nA:",
"role": "user"
},
{
"content": "How would Others feel as a result?",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_91724
|
[
{
"content": "In this task, you are given an input list A. You need to convert all the alphabets in the list with a number representing their position in the English alphabet. E.g., replace A by 1, B by 2, a by 1, b by 2, and so on.\n\nInput: Consider Input: ['4567', '6901', '6039', 'O', 'H', '3017', 'n', '1833', 'h', '8219', 'G', 'U', 'X', '4831', '9811', '2395', 'T', '8981', '8605', 'o', '5439', '8691', '59', '9861', 'b', 'x', '9013', 'r', '4359', 'F', '1189', 'E', 'l', 'S', '6133', '7949', 'R']\n\nOutput: 4567, 6901, 6039, 15, 8, 3017, 14, 1833, 8, 8219, 7, 21, 24, 4831, 9811, 2395, 20, 8981, 8605, 15, 5439, 8691, 59, 9861, 2, 24, 9013, 18, 4359, 6, 1189, 5, 12, 19, 6133, 7949, 18\n\n\nInput: Consider Input: ['N', '8821', 'U', 'X', 'N', '4125', 's', 'C', '9141']\n\nOutput: 14, 8821, 21, 24, 14, 4125, 19, 3, 9141\n\n\nInput: Consider Input: ['1929', 'h', '9849', '5701', '193', 'm', '1183', 'g', '9875', 'x', 'b', 'K', 'A', 'f', '9281', '5909', '9401', 'K', 'D', 'P', '573', '8883', 'z', 'q', '8215', 'g', 'P', 'V', '8889', '315', '3887']\n\n",
"role": "user"
},
{
"content": "Output: 1929, 8, 9849, 5701, 193, 13, 1183, 7, 9875, 24, 2, 11, 1, 6, 9281, 5909, 9401, 11, 4, 16, 573, 8883, 26, 17, 8215, 7, 16, 22, 8889, 315, 3887\n\n\n",
"role": "assistant"
}
] |
cot
|
cot_79259
|
[
{
"content": "The average of nine numbers is 15. The average of first four numbers is 11 and the average of last four numbers is 14. What is the middle number?\nOptions:\n(A) 19\n(B) 20\n(C) 35\n(D) 31\n(E) 27\n--\nThe total of nine numbers = 9X15 = 135\nThe total of first 4 and last 4 numbers is = 4 X 11+4 X 14 = 100\nSo, the middle number is (135 - 100 ) = 35 So the answer is: (C).\n-----\nIf x<0, y>0, and |x| < |y|, which of the following must be true?\nOptions:\n(A) x > y\n(B) y^2 > x^2\n(C) x^3 > y^2\n(D) –x < y\n(E) x < –y\n--\nCorrect Answer: (E)\nLet’s go through each answer choice: (A) can never be true, since no negative is greater than a positive. (B) doesn’t have to be true – consider what would happen if x = -2 and y = 1. (C) can never be true, as x^3 must be negative, and y^2 must be positive. (D) can never be true, since if x < 0, -x is the same thing as |x|, and |x| > y. (E) can be manipulated by multiplying both sides by -1, which gives us –x > y. Remember that x < 0, so –x = |x|, and y is positive, so |y| = y. Thus –x < y is the same statement as |x| > |y|, and (D) must be true. So the answer is: (D).\n-----\nIn 2005, 30 percent of the math department’s 40 students were female, and in 2007, 40 percent of the math department’s 65 students were female. What was the percent increase from 2005 to 2007 in the number of female students in the department?\nOptions:\n(A) 15%\n(B) 116%\n(C) 136%\n(D) 155%\n(E) 160%\n--\n",
"role": "user"
},
{
"content": "Female students in 2005 = 30% of 40 = 12\nFemale students in 2007 = 40% of 65 = 26\nPercentage increase = [(26 - 12)/12] *100 % = 116% So the answer is: (B).\n-----",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_84368
|
[
{
"content": "In this task, you are given inputs i and A, where i is an integer and A is a list. You need to list all the elements of A after the first i elements. i will always have a value less than the length of A.\n\nInput: Consider Input: 3, ['3743', 'R', 'C', 'n', 'v', '2503', 't', 'L']\n\nOutput: n, v, 2503, t, L\n\n\nInput: Consider Input: 12, ['r', 'n', 'e', '2445', '2155', '3707', 'l', '7199', 'P', '6619', '151', 'a', '8467', 'M', 'A', 'd', '6787', '7447', 'U', 'J', 'o', 't', '2757', 't', 'o']\n\nOutput: 8467, M, A, d, 6787, 7447, U, J, o, t, 2757, t, o\n\n\nInput: Consider Input: 2, ['u', '3785', '1763', '6015', '7367', 'i', '3165', '9731', 'U', '9085', 'K', '5201', 'I', '4423', '9393', '9989', 'u', 'x', 'k', '9735', '6155', '8699', '2677', '5871', 'B']\n\n",
"role": "user"
},
{
"content": "Output: 1763, 6015, 7367, i, 3165, 9731, U, 9085, K, 5201, I, 4423, 9393, 9989, u, x, k, 9735, 6155, 8699, 2677, 5871, B\n\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_85953
|
[
{
"content": "Detailed Instructions: You are given a statement written in Oriya. Choose the most logical word from the given 4 options which can be used to replace the <MASK> token in the statement. Output the word from the correct option .\nSee one example below:\nProblem: Statement: 'ରକନୁଦ୍ଦୀନ'ଙ୍କ ଶାସନ ବହୁତ କମ ସମୟ ପାଇଁ ଥିଲା । ଇଲତୁତମିଶଙ୍କ ବିଧବା , ଶାହା ତୁର୍କାନଙ୍କ ଶାସନ ଉପରେ ନିୟନ୍ତ୍ରଣ ରହି ପାରିନଥିଲା । ଭୋଗ ବିଳାସୀ ଏବଂ ଦାଇତ୍ୱହୀନ ରକନୁଦ୍ଦୀନଙ୍କ ବିପକ୍ଷରେ ଜନତା ମାନଙ୍କ ମଧ୍ୟରେ ଏହି ସୀମା ପର୍ଯ୍ୟନ୍ତ ଆକ୍ରୋଶ ଭାବ ଜାଗ୍ରତ ହୋଇଥିଲା କି , ୧ ନଭେମ୍ବର ୧୨୩୬ ମସିହାରେ ରକନୁଦ୍ଦୀନ ତଥା ତାଙ୍କ ମାତା , ଶାହା ତୁର୍କାନଙ୍କ ହତ୍ୟା କରିଦିଆଗଲା । ତାଙ୍କ ଶାସନ ମାତ୍ର ୬ ମାସର ଥିଲା । ଏହା ପରେ ସୁଲତାନଙ୍କ ପାଇଁ ଅନ୍ୟ କୌଣସି ବିକାଶର ଅଭାବରେ ମୁସଲମାନଙ୍କୁ ଏକ ମହିଳାଙ୍କୁ ଶାସନର ବାଗଡୋର ଦେବାକୁ ପଡ଼ିଥିଲା , ଏବଂ ପରେ ରଜିୟା ସୁଲତାନ <MASK>ର ଶାସିକା ରୂପେ ନିୟୋଜିତ ହୋଇଥିଲେ ।ଶାସନ କ୍ଷେତ୍ରରେ ରଜିୟଙ୍କ ରୁଚି ନିଜ ପିତାଙ୍କ ଶାସନ ସମୟରୁ ହିଁ ରହିଥିଲା ।\n\n Option A: ଭାରତ\n\n Option B: ଭଟିଣ୍ଡା\n\n Option C: ଦିଲ୍ଲୀ\n\n Option D: ରାଜସ୍ଥାନ\nSolution: ଦିଲ୍ଲୀ\nExplanation: The most suitable word from the given options to replace the <MASK> token is ଦିଲ୍ଲୀ, as Azi Sultan was the ruler of Delhi and at those times the remaining places aren't related .\n\nProblem: Statement: ଓଡ଼ିଶାର <MASK>,କନ୍ଧମାଳ,କଳାହାଣ୍ଡି, କୋରାପୁଟ, ମାଲକାନାଗିରି ଆଦି ଜିଲ୍ଲାରେ ଅନେକ ଆଦିବାସୀ ପରିବାର ରହିଛନ୍ତି । ଏମାନଙ୍କ ମଧ୍ୟରୁ ଗ୍ରାମବିକାଶ ୧୦,୦୦୦ ଗରିବ ଆଦିବାସୀ ପରିବାର ପାଇଁ ଯୋଜନା ପ୍ରସ୍ତୁତ କରିଛନ୍ତି । ଓଡ଼ିଶା ଆଦିବାସୀ ସଶକ୍ତିକରଣ ଓ ଜୀବିକା କାର୍ଯ୍ୟକ୍ରମ ସହ ମିଶି ଗ୍ରାମବିକାଶ ଗାଁଲୋକଙ୍କ ସହେଯାଗରେ ଜଳ ଓ ପରିମଳ ସମସ୍ୟା ଉପରେ କାମକରୁଛନ୍ତି । ଏବେ ସରକାରୀ ସହାୟତାରେ ଗାଁଗୁଡିକରେ ଉନ୍ନତ-ଆବାସ ଓ ମଜୁରୀ ଭିତ୍ତିକ ରୋଜଗାର,ଦକ୍ଷତା ବୃଦ୍ଧି ଦିଗରେ କାମକରୁଛି ଗ୍ରାମବିକାଶ ।\n\n Option A: ଗଜପତି\n\n Option B: ମାଲକାନାଗିରି\n\n Option C: ଆଫ୍ରିକା\n\n Option D: କୋରାପୁଟ\nSolution:",
"role": "user"
},
{
"content": "ଗଜପତି",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_86788
|
[
{
"content": "Craft one correct answer to the question given in input. To make it more interesting, try to use non-stereotypical language if possible. Make sure your correct answer is reasonably long, consistent with the context, and requires common sense (instead of explicit extraction from the context.) In your answer, use as few words as possible from the given context. Use a response that is uncommon/non-stereotypical, so that it is less predictable. To be less repetitive, please vary your language for each question.\n\n[Q]: Context: We both paused , our hearts racing not even daring to breathe incase they heard us . Then we heard them start to whisper again and we knew they would n't check into the noise further as I let out a silent sigh of relief . I felt Pete gently tug at my shirt , and as I turned to look at him he pointed towards the back of the shed and motioned for me to follow him . \nQuestion: Why did we pause ?\n[A]: So nobody would hear us .\n\n\n[Q]: Context: Doc and I did go out to dinner for our weekly Wednesday night date . He was craving a steak , so we went to one of those peanut - shells - in - the - floor places . He got his steak and I had chicken . The food was good , but the restaurant was too loud . \nQuestion: Why was the restaurant too loud ?\n[A]: People had to talk louder because of the music .\n\n\n[Q]: Context: Walking barefooted for five days straight , watching a turtle sleeping on a canopy of coral , saw more eels , got sunburnt ( for the first time in my entire life ... when I realised that I did n't have much melanin to protect my skin ) , battled some currents , getting cut , heard some great stories , got more cuts , starve off music for nearly a week , bad shower times ( once , the water came out drop . by . drop ) ... I ca n't really remember the rest . \nQuestion: Where may i be right now ?\n[A]:",
"role": "user"
},
{
"content": "A beach.\n\n\n",
"role": "assistant"
}
] |
cot
|
cot_60164
|
[
{
"content": "q: The average of 9 observations was 9, that of the 1st of 5 being 10 and that of the last 5 being 8. What was the 5th observation?\nOptions:\n(A) 9\n(B) 8\n(C) 5\n(D) 5\n(E) 4\na: Stream of consciousness: 1 to 9 = 9 * 9 = 81\n1 to 5 = 5 * 10 = 50\n5 to 9 = 5 * 8 = 40\n5th = 50 + 40 = 90 – 81 = 9 The answer is (A).\nquestion: If X is the sum of first 30 positive even integers and Y is the sum of first 30 positive odd integers, what is the value of x-y?\nPlease try to explain your answers\nOptions:\n(A) 10\n(B) 25\n(C) 30\n(D) 75\n(E) 100\nanswer: Stream of consciousness: First even minus first odd = 2-1 = 1;\nThe sum of first 2 even integers minus the sum of first 2 odd integers = (2+4)-(1+3) = 2;\nThe sum of first 3 even integers minus the sum of first 3 odd integers = (2+4+6)-(1+3+5) = 3;\nWe can see the patterns here, so the sum of first 30 positive even integers minus the sum of first 30 positive odd integers will be 30. The answer is (C).\nq: Steve traveled the first 2 hours of his journey at 40 mph and the last 2 hours of his journey at 80 mph. What is his average speed of travel for the entire journey?\nOptions:\n(A) 53.33 mph\n(B) 56.67 mph\n(C) 60 mph\n(D) 64 mph\n(E) 66.67 mph\na: Stream of consciousness: Average Speed = Total distance/ Total time = (40 * 2 + 80 * 2)/(2 + 2) = 240/4 = 60 The answer is (C).\nquestion: M is 30% of Q, Q is 20% of P and N is 50% of P. What is M / N\nOptions:\n(A) 3/28\n(B) 3/27\n(C) 3/21\n(D) 3/22\n(E) 3/25\nanswer: Stream of consciousness: Take P = 100, then N = 50, Q = 20, M = 6. So M/N = 3/25 The answer is (E).\nq: A boy multiplied 987 by a certain number and obtained 559981 as his answer. If in the answer both 9 are wrong and the other digits are correct, then the correct answer would be:\nOptions:\n(A) 553681\n(B) 555181\n(C) 555681\n(D) 556581\n(E) 556881\na: Stream of consciousness: 987 = 3 x 7 x 47\nSo, the required number must be divisible by each one of 3, 7, 47\n553681->(Sum of digits = 28, not divisible by 3)\n555181->(Sum of digits = 25, not divisible by 3)\n555681 is divisible by 3, 7, 47 The answer is (C).\nq: There are 10 female and 15 male in a work place. In how many ways can a person can be selected?\nOptions:\n(A) 20\n(B) 15\n(C) 18\n(D) 40\n(E) 25\na:",
"role": "user"
},
{
"content": "Stream of consciousness: No of ways = 10+ 15 = 25 The answer is (E).",
"role": "assistant"
}
] |
cot
|
cot_82878
|
[
{
"content": "Q: Given the sentence \"A skateboarder jumps another skateboard.\" is it true that \"A dog is rolling in the grass.\"?\nA: A skateboarder who jumps another skateboard is not a dog rolling in the grass simultaneously.\nThe answer is no.\nQUESTION: Test for natural language inference.\nPremise: \"Three children are sitting around a table reading books.\"\nHypothesis: \"The children are reading stories.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\n\nLet's solve it slowly: Three children are sitting around a table reading books implies reading stories.\nThe answer is yes.\n[QUESTION] Given the sentence \"People are talking to each other on the sidewalk.\" can we conclude that \"These people are good friends.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nPeople may talk to other people they are not friends with.\nThe answer is it is not possible to tell.\nQ: Given the sentence \"A man in a purple shirt and a black hat is taking a picture with a yellow digital camera.\" is it true that \"A man in a red shirt and blue cap is taking a picture with a green camera.\"?\nA: Someone wearing a purple shirt and black hat with a yellow camera would not be wearing a red shirt and blue cap while using a green camera at the same moment.\nThe answer is no.\nQUESTION: Premise: \"A woman with a blue umbrella stands next to a parking meter.\"\nHypothesis: \"The woman is in the gym.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: A woman either stands next to a parking meter or is in gym.\nThe answer is no.\nQUESTION: Premise: \"Four people sitting on a stone wall that overlooks trees and buildings.\"\nBased on this premise, can we conclude that the hypothesis \"Two best friends sit alone on a stone wall.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly:",
"role": "user"
},
{
"content": "Two best friends can't be sitting alone if there is a total of four of people.\nThe answer is no.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_89936
|
[
{
"content": "TASK DEFINITION: In this task, you are given a review of product in Polish language and a question whether this review has positive sentiment. You are expected to generate the answer. The output should be \"Yes\" or \"No\". Don't generate anything apart from \"Yes\", \"No\".\nPROBLEM: Text: Słaba antena. Może na 10tym piętrze bloku by lepiej działała. U mnie na parterze i pierwszym piętrze domku jednorodzinnego, kilka niedużych drzew na ogródku, antena stoi na parapecie na podwyższeniu i du*a blada czyli odnajduje 7 programów. Korzystałem z dwóch dekoderów jednego w smart tv Sony , a drugiego zewnętrznego. Oba znajdowały ledwo co 7 programów tvp \nQuestion: Is the text a positive review?\n\nSOLUTION: No\n\nPROBLEM: Text: Działa, ale głębia ostrości jest ustawiona na jakieś 10cm od obiektywu. Jak na coś co służy do wkładania w ciasne miejsca, to jest zdecydowanie słabo. Obraz powinien być wyraźny nawet z odległości paru milimetrów. No, chyba że mam jakiś wadliwy egzemplarz. W każdym razie pobawiłem się trochę, ale do zastosowań praktycznych obraz jest zbyt rozmyty.\nQuestion: Is the text a positive review?\n\nSOLUTION: No\n\nPROBLEM: Text: Duży opis w funkcji, a w rzeczywistości std. miernik. Obudowa wygląda na w miarę solidną, (tworzywo \"gumo-podobne\") chociaż czuć że raczej \"chińskie\". W instrukcji nie napisano gdzie zamontować baterie (rys. rozwiązałby problem) ani główne zabezpieczenie - należy się domyślić... Miernik nie do końca \"automatyczny\", ponieważ po wybraniu odpowiedniego zakresu pomiarowego (np. napięcia lub prądu) należy ręcznie przy pomocy dodatkowego przycisku (SEL) wskazać jaką wartość mierzymy: stałą czy zmienną (łatwo można się zapomnieć/pomylić...) Funkcja NCV, działa jak \"przyłożymy\" miernik bezpośrednio do gniazdka (tylko takim bez \"klapki\") natomiast nie nadaje się w żaden sposób do wykrywania kabli w ścianie (sprawdzone kilkukrotnie), szkoda bo byłby to fajny dodatek. Funkcja \"fazera\" podobnie, jak nie ma żadnego pola magnetycznego w okolicy pomiaru to jest OK, taśma LED-owa niedaleko gniazdka i miernik pokazuje głupoty - faza jest na L i N... Fajne silikonowe przewody o odpowiedniej długości - ciekawe jak długo wytrzymają :) Podświetlenie wyświetlacza OK, ale dlaczego włącza się \"latarka\" z tyłu miernika jednocześnie? - nie rozumiem... jak już to powinno się włączać każde osobno. Co do samych pomiarów i ich prawidłowości okaże się z czasem :)\nQuestion: Is the text a positive review?\n\nSOLUTION:",
"role": "user"
},
{
"content": "No\n\n",
"role": "assistant"
}
] |
cot
|
cot_80284
|
[
{
"content": "Q: Given the sentence \"Fresh fruit and veggies are lined up below a group of older women.\" can we conclude that \"The fruit and veggies are lined up in the supermarket for the female shoppers.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: it is not possible to tell\nCoT: Fruits and vegetables can be lined up in more places than a supermarket.\n****\nQ: Premise: \"A young girl in a bathing suit and goggles with a cast on her lower arm is diving off a starter block into a swimming pool with lane lines.\"\nHypothesis: \"A girl swimming in a lake.\"\nDo we know that the hypothesis entailed by the premise?\nA: no\nCoT: The girl can't be in a swimming pool and a lake at the same time.\n****\nQ: Test for natural language inference.\nPremise: \"Two women on rollerskates with helmets and elbow and knee pads jostle one another as they skate.\"\nHypothesis: \"The championship roller derby match is in progress.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: it is not possible to tell\nCoT: Two women skating and jostling each other aren't necessarily in a championship match.\n****\nQ: If \"The boy in the gray shirt seems to be explaining something to the girls sitting next to him.\" does that mean that \"The boy and girl are togehter.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: it is not possible to tell\nCoT:",
"role": "user"
},
{
"content": "A boy and a girl sitting next to each other are not necessarily togehter.\n****",
"role": "assistant"
}
] |
cot
|
cot_99866
|
[
{
"content": "[QUESTION] Can we conclude from \"A man sits on a pile of rugs by a building while three more men and a woman stand nearby.\" that \"A man sits on rugs that he is selling.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nSentence 1: A man sits on a pile of rugs by a building while three more men and a woman stand nearby. Sentence 2: A man sits on rugs that he is selling.\nThe answer is it is not possible to tell.\nQ: Premise: \"Family purchasing standing at a vending machine.\"\nBased on this premise, can we conclude that the hypothesis \"The family is standing by the counter.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: If they are standing at a vending machine then they are not standing by the counter.\nThe answer is no.\nQUESTION: Given the sentence \"Four bicyclists wearing yellow and orange vests are standing in front of a shack with mountains in the background.\" is it true that \"Four bikers are in front of a shack waiting for the owner to bring them food.\"?\n\nLet's solve it slowly: Bicyclists aren't necessarily bikers and the owner of the shack may not there to bring them food.\nThe answer is it is not possible to tell.\n[QUESTION] If \"A man in a collared shirt and a woman in a dress shopping in a supermarket.\" does that mean that \"Two men play with swords.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nMen are not the same thing as man and woman. Play and shopping are two different things.\nThe answer is no.\nQ: Given the sentence \"Two men are in a small boat and spraying water at something.\" is it true that \"Two sad men are in a small boat and spraying water at something.\"?\nA: The two men in the boat do not have to be sad.\nThe answer is it is not possible to tell.\n[QUESTION] If \"A man in a gray jacket and white shirt is leaning against a railing and talking to another man.\" does that mean that \"Two men are talking.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n",
"role": "user"
},
{
"content": "There are two men because a man is talking to another man and they are talking.\nThe answer is yes.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_75734
|
[
{
"content": "Given the task definition and input, reply with output. In this task, you're given an article, a question which often contains a blank, four options (associated with \"A\", \"B\", \"C\", \"D\") and the answer to that question. Your task is to classify whether the given answer is correct or not by providing \"Yes\" or \"No\", based on the article.\n\nArticle: Dear Sir, I am interested in your advertisement in the \"Arkadia Morning Mail\" for hostesses to be in charge of the welfare ,entertainment and guiding of British guests in your holiday centre in Ruusulinna. I am now a third-year student of English and History in the University of Gardenia but I am free from early June till late September.I have spent one year in London working in an English family and attending courses in English so I can speak this language fluently . My father has been a guide and I have often followed him and also myself acted as a guide to English-speaking groups.My studies and experience have made me familiar with many interesting places in my country.I am sociable,really interested in people and,at the same time,I am the one with common sense on whom people can depend. I put the address of the Manager of the local Tourist Information Office with the letter inside,who is ready to supply further information about me. If you are interested in my application ,I should be pleased with further information about these jobs,including the salary and general condition of employment. Yours faithfully, Polly Cosmos \n Question: What do you think the \"Arkadia Morning Mail\" is? \n Options: (A) It's a TV station. (B) It's a radio station. (C) It's a newspaper. (D) It's a company. \n Asnwer: A\n",
"role": "user"
},
{
"content": "No",
"role": "assistant"
}
] |
cot
|
cot_96010
|
[
{
"content": "[QUESTION] Can we conclude from \"A man is holding a sign directing people to a restaurant.\" that \"The people are tipping the man.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nIf the man is directing people to a restaurant then they would not be tipping him as he is not a worker in the restaurant.\nThe answer is no.\nQ: Test for natural language inference.\nPremise: \"A man dressed in green riding a bike.\"\nHypothesis: \"The man is sprinting to the finish line.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: Dressed in green does not imply sprinting to the finish line.\nThe answer is it is not possible to tell.\nQUESTION: Given the sentence \"A young girl with orange glasses working on making something out of wood.\" is it true that \"A young girl with green glasses is making something out of wood.\"?\n\nLet's solve it slowly: The girl's glasses are either orange or green. Orange and green are two different colors.\nThe answer is no.\n[QUESTION] Given the sentence \"A dark-haired woman wearing a gray shirt with a creme shirt over it and jeans walking down the parking lot past a blue car.\" can we conclude that \"A woman walks through a parking lot.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA parking lot can be inclined and a woman can be walking down.\nThe answer is yes.\nQ: Given the sentence \"A man wearing a green shirt and a dark colored vest is sitting at a table with a glass of water in front of him.\" can we conclude that \"The man is walking away from the table.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: He is either sitting at a table or walking away from the table.\nThe answer is no.\n[QUESTION] Given the sentence \"Person in blue top and shorts wearing a cap standing on a road with mountain with trees in the background.\" can we conclude that \"A person wants to climb the mountain.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n",
"role": "user"
},
{
"content": "Standing on a road with mountain does not mean wants to climb the mountain.\nThe answer is it is not possible to tell.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_80578
|
[
{
"content": "Q: Given a story, answer the question about the story. The question is the last sentence in the input. These stories can be difficult due to their length and how each story has at least one of the three following scenarios: the first is when the individual's belief matches reality, the second is when the individual's belief does not match reality, and the third is when an individual has a false belief about another individual's beliefs. The question will ask about the location of an object in the story with respect to either none or one of the three scenarios. Note that there are distractor sentences in each story that are unrelated to the question and are designed to confuse the reader.\nElla entered the bedroom. Logan entered the bedroom. The pumpkin is in the blue_bathtub. Ella moved the pumpkin to the green_cupboard. Owen entered the living_room. Ella entered the living_room. The lime is in the red_box. Phone rang. Owen moved the lime to the green_basket. Ella entered the bedroom. Emily entered the bedroom. The tomato is in the green_cupboard. Ella moved the tomato to the blue_bathtub. Owen entered the bedroom. Ella is in the bedroom. The tomato is in the blue_bathtub. Owen moved the tomato to the green_cupboard. Where will Ella look for the tomato?\nA:",
"role": "user"
},
{
"content": "green_cupboard",
"role": "assistant"
}
] |
cot
|
cot_50911
|
[
{
"content": "[QUESTION] Given the sentence \"A gray-haired person with glasses enjoys a sandwich.\" can we conclude that \"The man is enjoying drinks.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nContradiction between enjoying drinks and enjoying a sandwich in sentence 1.\nThe answer is no.\nQ: Given the sentence \"A family is observing a flying show.\" can we conclude that \"A family watching a flight show from a hill outside of their home.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: The family could be at a public venue watching the show and not necessarily on a hill outside of their home.\nThe answer is it is not possible to tell.\nQUESTION: Test for natural language inference.\nPremise: \"A person is standing in a green field in front of several colorful hot air balloons.\"\nHypothesis: \"The person in a field.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\n\nLet's solve it slowly: To be standing in a green field the person must be in the field.\nThe answer is yes.\n[QUESTION] Test for natural language inference.\nPremise: \"A man in a suit is giving a presentation while a lady in a black and white top sits.\"\nHypothesis: \"A person tries to impress his boss.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nGiving a presentation does not imply tries to impress his boss.\nThe answer is it is not possible to tell.\nQ: Premise: \"The racing dog has a muzzle and is wearing striped jersey# 8.\"\nHypothesis: \"The dogs are racing.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: A single dog in costume does not mean the dogs are there to be racing.\nThe answer is it is not possible to tell.\n[QUESTION] If \"Man talks on cellphone while standing near a dessert sign.\" does that mean that \"A person is looking at a sign.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n",
"role": "user"
},
{
"content": "A person talking on a phone might not be looking at the sign.\nThe answer is it is not possible to tell.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_91906
|
[
{
"content": "In this task, you will be shown a Persian passage and question. You need to write a answer for the question. Try to keep your answers as short as possible.\n\nQ: شریانهای دست آزمون آلن (به انگلیسی: Allen test) در پزشکی به روشی سریع برای درک میزان خون رادیال در بیمار گفته شده و بهترین تست پیش از انجام نمونهگیری در سنجش گاز خونی است. برای انجام این آزمون از بیمار میخواهیم چند بار دست خود را باز و بسته و سپس به صورت مشت شده نگه دارد. در حالیکه با دو انگشت روی مسیر شریان رادیال بیمار را فشار میدهیم از بیمار میخواهیم که مشت خود را باز کند و بلافاصله انگشت خود را از روی شریان بر میداریم، در صورتی که کف دست در عرض ۱۵ ثانیه یا کمتر پر خون و از حالت رنگ پریدگی خارج شود تست آلن را مثبت تلقی نموده و از شریان رادیال نمونهگیری گازومتری انجام میدهیم و مثبت بودن تست را در پرونده بیمار ثبت میکنیم. انجام این تست برای یکبار کافیست و در طول بستری نیازی به تکرار ندارد.نمونهٔ اولیهٔ این آزمون در سال ۱۹۲۹ میلادی توسط ادگار ون نایز آلن توصیف و ابداع شد. \n Question: چه جوری تست آلن مثبت می شود؟\n\nA: در صورتی که کف دست در عرض ۱۵ ثانیه یا کمتر پر خون و از حالت رنگ پریدگی خارج شود\n****\nQ: سیمان (به فرانسوی: Ciment) مادهای چسبنده است که قابلیت چسبانیدن ذرات به یکدیگر و بهوجود آوردن جسم یکپارچه و محکم از ذرات متشکله را دارا میباشد و از ترکیب مصالح آهکی، رس، و اکسیدهای معدنی در دمای ۱۴۰۰ تا ۱۵۰۰ درجه سانتیگراد ساخته میشود. به جسم حاصل، پس از حرارت دادن کلینکر گویند و از آسیاب کردن آن به همراه مقدار مناسبی سنگ گچ سیمان تیپهای مختلف بدست میآید و همچنین اضافه نمودن پوزولان به کلینکر و گچ سیمان پوزولانی حاصل میشود. اندازه دانههای کلینکر۲۰–۵ میلیمتر و رنگ آن سبز تیره میباشد. ولی کشف سیمان به شکل امروز مربوط است به یک نفر بنای انگلیسی بنام ژوزف اسپدین که از پختن آهک و خاک رس در حرارت بالا و آسیاب کردن آن موفق شد ابتداییترین نوع سیمان را کشف نموده و آن را در تاریخ ۲۱ اکتبر ۱۸۲۴ به نام خود در انگلستان ثبت نماید و نام محصول به دست آمده را سیمان پرتلند گذاشت. اینکه از چه تاریخی مصرف سیمان در ایران باب شدهاست چندان مشخص نیست ولی آنچه که مسلم است ورود سیمان به ایران توسط خارجیها بودهاست که از آن برای ساختن بناهایی نظیر کلیساها و سفارتخانهها و تأسیسات بندری استفاده شدهاست. ژوزف اسپدین نخستین شخصی بود که سیمان را در اوایل قرن نوزدهم در انگلستان به ثبت رسانده و آن را ابتدا برای ساخت فانوس دریایی مورد استفاده قرار داد. \n Question: سیمان از چه مواد تشکیل شده است.\n\nA: از ترکیب مصالح آهکی، رس، و اکسیدهای معدنی\n****\nQ: در گذشته آشپزخانه تنها فضایی بود برای امور مربوط به پخت و پز و محیطی کاملا جدا از فضاهای اصلی خانه داشت. مطبخ به دلیل بیاهمیت بودن، معمولا در گوشههای بنا و پشت اتاقهای اصلی قرار میگرفت. نور و تهویه در مطبخ به وسیله روزنههای ایجاد شده در سقف تأمین میشد. همچنین آن را محیطی کثیف و بیاهمیت میدانستند فاقد هرگونه تزئینات و مبلمان خاصی بود. آشپزخانه یا مطبخ به مکانی در خانه، رستوران یا هر جای دیگری میگویند که در آنجا غذا را میپزند. یک آشپزخانه مناسب دارای شرایط زیر است: لزوم نورپردازی مناسب، لزوم جریان داشتن هوا. ضوابط معماری یک آشپزخانه: موقعیت آشپزخانه در خانه، مثلث کار در آشپزخانه، محل قرارگیری وسایل آشپزخانه. انواع آشپزخانه: آشپزخانه ساده یا خطی، آشپز خانه با دو ردیف کابینت، آشپزخانه ال شکل، آشپزخانه یو شکل، آشپزخانه جزیرهای. در خانههای امروزی آشپزخانه تاثیر مستقیمی روی دکوراسیون خانه دارد. تا جایی که توانسته طراحان را برای طراحی فضایی کاربردی و همچنین دارای زیباییهای بصری به چالش بکشد. در دنیای مدرن آشپزخانه نه تنها محیط مناسبی برای آشپزی و تهیه غذاست؛ بلکه محیط مناسبیست برای سرو غذا و گذراندن زمان نسبتا زیادی در کنار خانواده است. لوازم آشپزخانه: موادی و مصالحی که برای دیوار استفاده میشوند، کفش پوش، کابینتها و رویه آنها، وسایل آشپزخانه جزیره، اجاق گاز، صندلیهای آشپزخانه، محل قرار گیری هود، سینک و نوع آن، جنس و نوع شیرآب، نوع گرمایش و سرمایش، نوع سقف کاذب، مسائل روشنایی، کاشی بین کابینتی. \n Question: شکلهای مختلف آشپزخانه را نام ببرید؟\n\nA:",
"role": "user"
},
{
"content": "آشپزخانه ساده یا خطی، آشپز خانه با دو ردیف کابینت، آشپزخانه ال شکل، آشپزخانه یو شکل، آشپزخانه جزیرهای\n****\n",
"role": "assistant"
}
] |
cot
|
cot_94943
|
[
{
"content": "**Q**\nYes / no, is the following a verifiable fact?\n\"The One-child policy prevents parents from having more than 1 kid.\"\n**A**\nno\nThis is not true, if the miracle of twins were to occur, then the parents would not be penalized.\nIs the following sentence factually correct?\n\"Paul I of Russia passed away from natural causes.\"\nOptions:\n- yes\n- no\nno\nPaul I of Russia was assassinated in the early 1800's by dismissed officers.\n**Q**\nYes / no, is the following a verifiable fact?\n\"The Boat Race between John and Peter attracts many neighbors to watch.\"\n**A**\nno\nThe Boat Race is actually a university rowing event in the United Kingdom and not a random rowing competition among people.\nDoes the following sentence make sense?\n\"Bipolar disorder used to be known as Manic Depressive Disorder.\"\nOptions:\n- yes\n- no\nyes\nBipolar Disorder is the newer term for the disorder.\n**Q**\nIs the following a factual statement?\n\"The Winter War between Finland and the Soviet Union occurred in the twentieth century.\"\nOptions:\n- yes\n- no\n**A**\nyes\nThe Winter War was fought between 1939 and 1940.\n**Q**\nClaim: \"Ammonia has a pungent and stinging odor.\"\nIs the claim above correct, and can it be verified by human common sense and without a web search?\nOptions:\n- yes\n- no\n**A**\n",
"role": "user"
},
{
"content": "yes\nMany people know ammonia for the sharp and acrid scent it has.",
"role": "assistant"
}
] |
cot
|
cot_51068
|
[
{
"content": "[QUESTION] Premise: \"A mam and woman riding bicycles down a city street.\"\nHypothesis: \"The man and woman are driving a car.\"\nDo we know that the hypothesis entailed by the premise?\nEither riding bicycles or driving a car is possible. Not together.\nThe answer is no.\nQ: Given the sentence \"A girl in yellow dress is standing with her eyes closed in a busy park.\" is it true that \"A girl is standing.\"?\nA: The girl must have a dress on to be in a busy park.\nThe answer is yes.\nQUESTION: Given the sentence \"An attractive young woman in a blue jacket walks around a train station.\" is it true that \"An attractive older woman in a red jacket runs around a train station.\"?\n\nLet's solve it slowly: A young woman is different than an older woman. A red jacket is different than a blue jacket.\nThe answer is no.\n[QUESTION] If \"Two people sit on a dock with a sunset in the background.\" does that mean that \"The couple listen to the frogs at dusk.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nTwo people does not imply couple and sit does not imply to listen to frogs.\nThe answer is it is not possible to tell.\nQ: Given the sentence \"A group of firefighters all dressed up in their gear standing on a road.\" can we conclude that \"The firefighters are ready for bed.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: Firefighters standing on a road would not be ready for bed.\nThe answer is no.\n[QUESTION] Premise: \"An older man is doing a karate pose.\"\nHypothesis: \"A man sleeping on a couch.\"\nDo we know that the hypothesis entailed by the premise?\n",
"role": "user"
},
{
"content": "The sleeping man contradicts the man doing a karate pose in first sentence.\nThe answer is no.",
"role": "assistant"
}
] |
cot
|
cot_92261
|
[
{
"content": "Q: If \"An enthusiastic crowd of people kicking a red ball around on a grassy field.\" does that mean that \"People kick a red ball.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: yes\nChain-of-thought: People kicking a red ball surely do kick a red ball.\n\nQ: Test for natural language inference.\nPremise: \"A woman in a brown jacket passes by a column with an advertisement pasted on it.\"\nHypothesis: \"Featuring red lettering and a person's face.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: no\nChain-of-thought: A woman in a red jacket passing a stand with two girls selling lemonade at it.\n\nQ: Given the sentence \"Two emergency workers looking under a train.\" is it true that \"Worker looking under a train.\"?\nA: yes\nChain-of-thought: Two emergency workers were in need to look after the train when there was a trouble in starter.\n\nQ: Test for natural language inference.\nPremise: \"A young man in black shorts is jumping in the waves on the beach.\"\nHypothesis: \"A young man is jumping in the waves.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: yes\nChain-of-thought:",
"role": "user"
},
{
"content": "A young man jumping in the waves on the beach must be jumping in the waves.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_82360
|
[
{
"content": "In this task, you're given a statement and three sentences as choices. Your job is to determine the neutral choice based on your inference from the statement and your commonsense knowledge. The neutral choice is a sentence that neither agrees nor disagrees with the statement. Indicate your answer as '1', '2', or '3', corresponding to the choice number of the selected sentence. If sentence X agrees with sentence Y, one's correctness follows from the other one. If sentence X disagrees with sentence Y, they can not be correct at the same time.\n\nExample Input: Statement: where am i Choices: 1. Where am I? 2. What am I? 3. I'm in America. \nExample Output: 3\n\nExample Input: Statement: Such data include narratives of events written by participant observers, accounts of what the participants understood about an event, reports of what was said at a meeting or an interview, observational records of how an event took place, and statements of impressions about what was going on, why it was happening, and how people felt about it, themselves, or each other. Choices: 1. The data was made up of objective facts so it would not be influenced by mass opinion subject to influence by ulterior motive and gossip of other people as that would be unfair to the target of study in the case. 2. Data may be narratives of events as experienced by observers including any details, spoken memory of what was said and their overall impression and personal feelings. 3. The data on the Child Protective Services Report gathered information from all family members involved to determine safety in the home by interviewing them about narratives of events as experienced by family members including any details, spoken memory of what was said and overall impression and personal feelings. \nExample Output: 3\n\nExample Input: Statement: We also cannot stand their dog. Choices: 1. We love their dog. 2. Their dog is a Labrador. 3. We hate their dog.\nExample Output:",
"role": "user"
},
{
"content": "2\n\n",
"role": "assistant"
}
] |
cot
|
cot_88248
|
[
{
"content": "Next to is the same as beside. Also the second sentence is less descriptive than the first.\nThe question and answer are below.\nPremise: \"A woman in a pink sweater looks pensive next to a crowd of laughing women.\"\nBased on this premise, can we conclude that the hypothesis \"A woman in pink stands beside a crowd of women.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\nyes\n\nEleven children sitting next to each other on a stoop in front of a blue grating while holding objects in front of their eyes does not imply they are posing for a photo for their family.\nThe question and answer are below.\nPremise: \"Eleven children sit next to each other on a stoop in front of a blue grating while holding objects in front of their eyes.\"\nBased on this premise, can we conclude that the hypothesis \"Eleven children are posing for a photo for their family.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\nit is not possible to tell\n\nA child wearing a white shirt is holding a yellow shovel on a beach does not necessary that the child is homless.. So what could be the question?\nQuestion followed by answer: Premise: \"A child wearing a white shirt is holding a yellow shovel on a beach.\"\nHypothesis: \"The child is homless.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- it is not possible to tell\n- no\nit is not possible to tell\n\nAn outdoor artwork is an artwork displayed on the exterior of a building.\nThe question and answer are below.\nGiven the sentence \"A man wears a black cape in the parking lot of a building that has artwork displayed on the exterior.\" can we conclude that \"A man can see outdoor artwork.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nyes\n\nNot all causes for protest are causes protesters are affected by.\nThe question and answer are below.\nGiven the sentence \"A man protests in support of a cause.\" is it true that \"A man supports a cause he is affected by.\"?\nit is not possible to tell\n\nJumping for Frisbee and playing fetch could be the same thing.\nThe question and answer are below.\n",
"role": "user"
},
{
"content": "Premise: \"Dog jumping for frisbee.\"\nHypothesis: \"The dog was playing fetch.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- it is not possible to tell\n- no\nyes",
"role": "assistant"
}
] |
cot
|
cot_90251
|
[
{
"content": "Q: Given the sentence \"A black dog is running through the water.\" is it true that \"A black dog is at the beach.\"?\nA: The black dog could be at the lake and not the beach.\nThe answer is it is not possible to tell.\nQUESTION: If \"A man in a black sweater with a red undershirt playing a trumpet in front of a lighted christmas tree.\" does that mean that \"A man in a black sweater with a red undershirt.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: A man is wearing a black sweater with a red undershirt.\nThe answer is yes.\n[QUESTION] Test for natural language inference.\nPremise: \"Two females looking at a mountain in a park wearing bathing suits.\"\nHypothesis: \"Women wearing bathing suits look at a goat climbing a mountain.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nThe women could be young girls somewhere other than a park where there were no goats climbing.\nThe answer is it is not possible to tell.\nQ: Premise: \"The man in the green shirt is running on the field.\"\nHypothesis: \"The man is playing a sport with his friends.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: Running in a field desn't mean the man is playing a sport.\nThe answer is it is not possible to tell.\nQUESTION: Given the sentence \"Three teenagers drink slurpees outside a convienience store.\" is it true that \"Teenagers eating popcorn at the movies.\"?\n\nLet's solve it slowly: You cannot drink slurpees while eating popcorn as a person can only do one of those at a time.\nThe answer is no.\nQUESTION: Test for natural language inference.\nPremise: \"Two friends hold trophies.\"\nHypothesis: \"Two people have awards.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\n\nLet's solve it slowly:",
"role": "user"
},
{
"content": "Two friends are two people and if they hold trophies then they have awards.\nThe answer is yes.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_95230
|
[
{
"content": "Q: Given the sentence \"A black dog is running through the water.\" is it true that \"A black dog is at the beach.\"?\nA: The black dog could be at the lake and not the beach.\nThe answer is it is not possible to tell.\nQUESTION: If \"A man in a black sweater with a red undershirt playing a trumpet in front of a lighted christmas tree.\" does that mean that \"A man in a black sweater with a red undershirt.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: A man is wearing a black sweater with a red undershirt.\nThe answer is yes.\n[QUESTION] Test for natural language inference.\nPremise: \"Two females looking at a mountain in a park wearing bathing suits.\"\nHypothesis: \"Women wearing bathing suits look at a goat climbing a mountain.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nThe women could be young girls somewhere other than a park where there were no goats climbing.\nThe answer is it is not possible to tell.\nQ: Premise: \"The man in the green shirt is running on the field.\"\nHypothesis: \"The man is playing a sport with his friends.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: Running in a field desn't mean the man is playing a sport.\nThe answer is it is not possible to tell.\nQUESTION: Given the sentence \"Three teenagers drink slurpees outside a convienience store.\" is it true that \"Teenagers eating popcorn at the movies.\"?\n\nLet's solve it slowly: You cannot drink slurpees while eating popcorn as a person can only do one of those at a time.\nThe answer is no.\nQUESTION: Test for natural language inference.\nPremise: \"Two friends hold trophies.\"\nHypothesis: \"Two people have awards.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\n\nLet's solve it slowly:",
"role": "user"
},
{
"content": "Two friends are two people and if they hold trophies then they have awards.\nThe answer is yes.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_89117
|
[
{
"content": "instruction:\nIn this task, you are given triplets. Each triplet is in the form of [subject, predicate, object]. Your task is to generate proper sentence that utilizes these triples. The objective is to construct a sentence that (a) captures the facts specified in the triples and (b) is a well-formed sentence easily understandable by a human. All triple values need not be used directly in the sentence as long as the facts are adequately captured.\nquestion:\n[['The Rice Boat', 'food', 'Indian'], ['The Rice Boat', 'customer rating', '5 out of 5'], ['The Rice Boat', 'area', 'riverside'], ['The Rice Boat', 'familyFriendly', 'no']]\nanswer:\nThe Rice Boat serves Indian food. It has a customer rating of 5 out of 5 and is located in the riverside area and is not family friendly.\n\n\nquestion:\n[['A.C. Chievo Verona', 'MANAGER', 'Rolando Maran'], ['Rolando Maran', 'CLUB', 'Unione Triestina 2012 S.S.D.'], ['Rolando Maran', 'CLUB', 'Carrarese Calcio']]\nanswer:\nAssociazione Calcio ChievoVerona is managed by Rolando Maran, who plays for Unione Triestina 2012 S.S.D at the Carrarese Calcio.\n\n\nquestion:\n[['Bacon Explosion', 'COUNTRY', 'United States'], ['Bacon Explosion', 'MAIN_INGREDIENTS', '\"Bacon,sausage\"'], ['Bacon Explosion', 'INGREDIENT', 'Sausage'], ['Bacon Explosion', 'REGION', 'Kansas City metropolitan area']]\nanswer:\n",
"role": "user"
},
{
"content": "The main ingredients of the Bacon Explosion are bacon and sausage, and comes from the Kansas City metropolitan area in the United States.\n\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_73950
|
[
{
"content": "Teacher:In this task, you're given an article and an answer. Your task is to generate the fill-in-the-blank question for this answer based on the given article. The blanks are always at the end of the question, and can be filled with more than one word or phrase.\nTeacher: Now, understand the problem? Solve this instance: Article: Several years ago, I had to replace a receptionist for my unit. Before I advertised for the position, I was approached by another manager, and asked ifl would consider a transfer from his staffinstead of opening a new competition. My natural question was to ask who he wanted me to consider and why. It appeared from his description of this employee, Maria, that she was having a lot of problems performing her duties, and had difficulties with her boss, and did not appear to respond to any attempts he, the manager, had made to settle the issues. Now, after listening to his explanation, I really had severe doubts. What crossed my mind, after this discussion, was that he wanted me to take a problem off his hands. I told him I would think about it and would let him know the next day. As promised, after thinking more about this potential performance issue, I decided that I would agree to speak with Maria privately before I made any decision. And, what I found out during this interview, left me deep in thought. As it tumed out, the performance issue appeared to result from working for a boss who never extended a good morning. greeting, never gave a word of encouragement, and was constantly changing the work load and routines. The end result was a totally ruined employee who was unconfident, hated to see a new work day start. I decided to accept her transfer to my unit. What started out as a shy, withdrawn and frightened employee turned out to be one of the most productive and loyal employee that I had eyer worked with. Maria couldn't do enough and was constantly asking for more and for more responsibility. I was morethan happy to give her what she needed-praise for work well done, respect as a person, and encouragement for doing well in anything she dealt with. Sometimes, we are guilty of holding others back from accomplishing or doing, or developing as they should or could. It may be a wise idea that we all look in the mirror, from time to time, to seewhat we are really like. \n Answer: was a problem to her boss\nStudent:",
"role": "user"
},
{
"content": "After hearing his colleague's description of Maria, the writer thought that Maria _ .",
"role": "assistant"
}
] |
cot
|
cot_91336
|
[
{
"content": "Q: Given the sentence \"A trolley driver is telling people to move off of the street.\" can we conclude that \"A car is being blocked by people.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: Telling people to move off the street doesn't imply a car is being blocked by people.\nThe answer is it is not possible to tell.\nQUESTION: Given the sentence \"A construction worker is fixing a large machine.\" is it true that \"A man fixes a tractor.\"?\n\nLet's solve it slowly: The man could be fixing a different large machine than a tractor.\nThe answer is it is not possible to tell.\n[QUESTION] Can we conclude from \"Snowboarder holding a blue snowboard and a green snowboard.\" that \"The snowboarder is headed down a steep slope.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nThe snowboarder cannot be holding a blue snowboard and a green snowboard while being headed down a slope.\nThe answer is no.\nQ: Test for natural language inference.\nPremise: \"A man in combat fatigues surveys the scene using binoculars.\"\nHypothesis: \"An army man is searching for enemies in a combat zone.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: The man is in combat fatigues but he isn't necessarily an army man. The man isn't necessarily searching for enemies in a combat zone.\nThe answer is it is not possible to tell.\nQUESTION: Can we conclude from \"The guy is wearing a blue shirt and doing an ollie.\" that \"A skateboarder is doing stunts.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\n\nLet's solve it slowly: Just because The guy is wearing a blue shirt and doing an ollie doesn't mean he is a skateboarder.\nThe answer is it is not possible to tell.\nQUESTION: Test for natural language inference.\nPremise: \"Two bicyclists race down a street.\"\nHypothesis: \"Two people drive monster trucks in a rally.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\n\nLet's solve it slowly:",
"role": "user"
},
{
"content": "Bicyclists riding bike cannot drive monster trucks at the same time.\nThe answer is no.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_78647
|
[
{
"content": "Given the task definition and input, reply with output. In this task, you're given the title and three arbitrary sentences out of a five-sentence story. You are also given three additional sentence options, a, b, and c, that may or may not belong to the story. Your job is to pick the two options that seamlessly connect with the rest of the story; note that the selected choices may fit into the story at any point. Indicate your selected choices in order, i.e., as 'ab'/'bc'/'ac' and not as 'ba'/'ca'/'cb'. If options are equally plausible, pick the ones that make more sense.\n\nTitle: One day all of the admins had an argument in a group email. They all decided to overthrow Paul and kick him out of the group. Paul is now no longer a part of the group he created. Choices: a. Suddenly hundreds of bees flew out and stung him all over his body! b. He added 3 other people to help out and be admins with him. c. Paul created a facebook group.\n",
"role": "user"
},
{
"content": "bc",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_87581
|
[
{
"content": "TASK DEFINITION: In this task, you are given an input list A. You need to find all the elements of the list that are alphabets in the same order as they appear in the list A. Do not change their case/capitalization.\nPROBLEM: ['T', 'G', 'I', 'k', '4897', '6709', '4113', '9587', 'w', 'a', 'o', 'H', '7261', 'V', 'H', 'G', 'L', 'f', '2481', 'H', '2569']\n\nSOLUTION: T, G, I, k, w, a, o, H, V, H, G, L, f, H\n\nPROBLEM: ['9989', '3931', '1461', 'i', 'S', 'M']\n\nSOLUTION: i, S, M\n\nPROBLEM: ['R', '7007', '4991', '5231', '3745', '6813', 'g', 'P', 'J', 'y', '689', 'k', '3623', 'l', 'Y', 'b', '9433', '9651', '7315', 'w', 'X', 'p', 'j', 'C', 'd', 'M', '7667']\n\nSOLUTION:",
"role": "user"
},
{
"content": "R, g, P, J, y, k, l, Y, b, w, X, p, j, C, d, M\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_74513
|
[
{
"content": "Given the task definition and input, reply with output. Given a story, answer the question about the story. The question is the last sentence in the input. These stories can be difficult due to their length and how each story has at least one of the three following scenarios: the first is when the individual's belief matches reality, the second is when the individual's belief does not match reality, and the third is when an individual has a false belief about another individual's beliefs. The question will ask about the location of an object in the story with respect to either none or one of the three scenarios. Note that there are distractor sentences in each story that are unrelated to the question and are designed to confuse the reader.\n\nOliver entered the master_bedroom. Ella entered the master_bedroom. The persimmon is in the blue_pantry. Oliver moved the persimmon to the blue_bathtub. Oliver is in the master_bedroom. Ella is in the master_bedroom. The onion is in the blue_bathtub. Oliver moved the onion to the blue_pantry. Jack entered the den. Aiden entered the den. The cabbage is in the green_suitcase. Jack moved the cabbage to the blue_suitcase. Ella entered the staircase. Oliver entered the staircase. The strawberry is in the green_treasure_chest. Ella moved the strawberry to the blue_envelope. Where does Ella think that Oliver searches for the strawberry?\n",
"role": "user"
},
{
"content": "blue_envelope",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_13514
|
[
{
"content": "Question: Sentence A: Or, to put it another way, in the sense of asking an entirely different Is it really a requirement of sophistication that a place provides good bookstores, movies, plays, museums, music, cuisines, and an opportunity for erotic and intellectual freedom?\n\nSentence B: Is it required that sophisticated places have classical music concerts?\n\nIf sentence A is true, how about sentence B?\nOPTIONS:\n- yes\n- it is not possible to tell\n- no\n\nAnswer: it is not possible to tell\n\n\nQuestion: Sentence A: This monumental construction covers a140-sq-m (1,500-sq-ft) area, with a Great Hypostyle Hall of 122 columns in nine rows, 21 m (70 ft) high, and is considered one of the finest ancient structures in the country.\n\nSentence B: The construction is thought of as a fine structure.\n\nIf sentence A is true, how about sentence B?\nOPTIONS:\n- yes\n- it is not possible to tell\n- no\n\nAnswer: yes\n\n\nQuestion: Sentence A: The other received limited funding, and ultimately was provided a very short grant.\n\nSentence B: The other got a large loan to be paid back over five years.\n\nIf sentence A is true, how about sentence B?\nOPTIONS:\n- yes\n- it is not possible to tell\n- no\n\nAnswer: no\n\n\nQuestion: Sentence A: oh very interesting um over the years of course by uh my grandparents used to give me silver dollars so i've got a few of those tucked away but\n\nSentence B: I used to get silver dollars from my grandparents.\n\nIf sentence A is true, how about sentence B?\nOPTIONS:\n- yes\n- it is not possible to tell\n- no\n\nAnswer:",
"role": "user"
},
{
"content": "yes",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_91353
|
[
{
"content": "In this task, you're given a context passage, a question, and three answer options. Your task is to return an incorrect answer option to the question from the choices given. For all questions, only one of the three answer options is correct. Pick one of the two incorrect answer options as the output.\n\n[Q]: Context: Even though Ash told him many times to leave it alone, Ash's parents saw that Lee was riding Ash's bike home from school. \n Question: How would you describe Lee? \n Options: (A) Someone that doesnt care what others tell him (B) sorry that he ignored Ash's request (C) happy that he got away with it\n[A]: B\n\n\n[Q]: Context: Alex took Cameron on a date even though they had troubles in the past. \n Question: What will Cameron want to do next? \n Options: (A) show them a good time (B) forgive Cameron (C) show them a bad time\n[A]: B\n\n\n[Q]: Context: Robin gave the beggar money out of their wallet, despite protests from their partner. \n Question: How would their partner feel as a result? \n Options: (A) like Robin got swindled (B) compassionate (C) generous\n[A]:",
"role": "user"
},
{
"content": "B\n\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_84881
|
[
{
"content": "In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to collate all the alphabetical elements at the start of the list followed by all the numerical elements of the list. Maintain the order in which the alphabetical elements appear in the given input list, and do the same for the numerical elements.\n\nEx Input:\n['3727', 'b', '659', 'S', 'W', 'm', 'U', '8483', 'H', '4495', '6269', '8761', 'p', 'u', 'u', '3611', 't', 'T', '785', '3587', '2139', '7165', '4671', '871', 'K', '3257', '8447', 'r', 'c', '765', '2979']\n\nEx Output:\nb, S, W, m, U, H, p, u, u, t, T, K, r, c, 3727, 659, 8483, 4495, 6269, 8761, 3611, 785, 3587, 2139, 7165, 4671, 871, 3257, 8447, 765, 2979\n\n\nEx Input:\n['m', 'f', '3429', '6557', 'U', '4541', 'o']\n\nEx Output:\nm, f, U, o, 3429, 6557, 4541\n\n\nEx Input:\n['I', 'F', '5381', 'K', '2515', 'o', '8129', '6779', '4707', 'S', '4621', 'f', '7277', 'I', '5421', '6983', 'L', '5657', '5443', '4603', '8549', '1569', 'A', 'H', 'w', 'B', '1015', 'F', '6147', 'b', 'w', 'j', '7273', '1027', '8001', 'G', 'q']\n\nEx Output:\n",
"role": "user"
},
{
"content": "I, F, K, o, S, f, I, L, A, H, w, B, F, b, w, j, G, q, 5381, 2515, 8129, 6779, 4707, 4621, 7277, 5421, 6983, 5657, 5443, 4603, 8549, 1569, 1015, 6147, 7273, 1027, 8001\n\n\n",
"role": "assistant"
}
] |
cot
|
cot_88984
|
[
{
"content": "**Q**\nIs the following a factual statement?\n\"People look to Zoology sometimes to explain human behavior.\"\nOptions:\n- yes\n- no\n**A**\nyes\nZoology, the study of animals, is sometimes consulted to compare people and non-human animals, elucidating some human behavior.\nClaim: \"Finding Dory describes a child that was kidnapped.\"\nIs the claim above correct, and can it be verified by human common sense and without a web search?\nOptions:\n- yes\n- no\nno\nMost people know that this is called an Amber Alert.\n**Q**\nIs the following sentence factually correct?\n\"The Golden Gate Bridge appears yellow in color.\"\nOptions:\n- yes\n- no\n**A**\nno\nThe Golden Gate Bridge is actually red in color.\nIs the following a factual statement?\n\"Douglas Adams built a bridge from Memphis, Tennessee to Lubbock, Texas in the late 18th Century.\"\nOptions:\n- yes\n- no\nno\nThe 18th Century ended long before Douglas Adams was born and there is no bridge from Memphis to Lubbock.\n**Q**\nDoes the following sentence make sense?\n\"During Mike Tyson Vs. Evander Holyfield III, Holyfield bit Tyson back on the neck drawing blood during the 6rd round.\"\nOptions:\n- yes\n- no\n**A**\nno\nThere was never a Tyson Vs. Holyfield III.\n**Q**\nIs the following sentence factually correct?\n\"The Cherokee Indians were forcibly removed from their ancestral lands by white settlers.\"\nOptions:\n- yes\n- no\n**A**\n",
"role": "user"
},
{
"content": "yes\nCherokee Indians were among many tribes forced to walk the Trail of Tears.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_95548
|
[
{
"content": "**Q**\nIs the following a factual statement?\n\"People look to Zoology sometimes to explain human behavior.\"\nOptions:\n- yes\n- no\n**A**\nyes\nZoology, the study of animals, is sometimes consulted to compare people and non-human animals, elucidating some human behavior.\nClaim: \"Finding Dory describes a child that was kidnapped.\"\nIs the claim above correct, and can it be verified by human common sense and without a web search?\nOptions:\n- yes\n- no\nno\nMost people know that this is called an Amber Alert.\n**Q**\nIs the following sentence factually correct?\n\"The Golden Gate Bridge appears yellow in color.\"\nOptions:\n- yes\n- no\n**A**\nno\nThe Golden Gate Bridge is actually red in color.\nIs the following a factual statement?\n\"Douglas Adams built a bridge from Memphis, Tennessee to Lubbock, Texas in the late 18th Century.\"\nOptions:\n- yes\n- no\nno\nThe 18th Century ended long before Douglas Adams was born and there is no bridge from Memphis to Lubbock.\n**Q**\nDoes the following sentence make sense?\n\"During Mike Tyson Vs. Evander Holyfield III, Holyfield bit Tyson back on the neck drawing blood during the 6rd round.\"\nOptions:\n- yes\n- no\n**A**\nno\nThere was never a Tyson Vs. Holyfield III.\n**Q**\nIs the following sentence factually correct?\n\"The Cherokee Indians were forcibly removed from their ancestral lands by white settlers.\"\nOptions:\n- yes\n- no\n**A**\n",
"role": "user"
},
{
"content": "yes\nCherokee Indians were among many tribes forced to walk the Trail of Tears.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_91546
|
[
{
"content": "TASK DEFINITION: In this task, the input is a set of dialogues between a user and an assistant. You need to find the dialogue that is basically a response given to a question or an aspect of the user.\nPROBLEM: Hello, please can you tell me about New South Wales \n That's good to know. Can you please tell me about their education system \n Please do you know how many institution are there in New South Wales? \n Please I'd like to know about the geography of New South Wales? \n New South Wales is one of the states of Australia. It is the oldest state there, and sometimes called the \"Premier State\".\n\nSOLUTION: New South Wales is one of the states of Australia. It is the oldest state there, and sometimes called the \"Premier State\".\n\nPROBLEM: That's really unfortunate. What else do you know about it? \n Cool. Do you know anything about its economy? \n The 3 biggest ports of Latvia are located in Riga, Ventspils and Liepaja. \n You're welcome. \n Hi, can you tell me about the demographics of Latvia?\n\nSOLUTION: The 3 biggest ports of Latvia are located in Riga, Ventspils and Liepaja.\n\nPROBLEM: Yes, I am interested in learning the demographics. \n You too! \n Sorry, I'm not sure about that would you like to know about their economy? \n Ok, now what can you tell me about the twin towns and sister cities? \n Of course. It seems that about half of the popullation is Russian Orthodox.\n\nSOLUTION:",
"role": "user"
},
{
"content": "Of course. It seems that about half of the popullation is Russian Orthodox.\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_50353
|
[
{
"content": "[Q]: Cameron played games on Skylar's phone and then dropped it in the toilet. Given that the answer to a question is \"very stupid\", what is the question?\n****\n[A]: Skylar and Cameron will feel how afterwards?\n\n\ninput: Please answer the following: Remy asked Jordan to dinner for the third time that night. Given that the answer to a question is \"was hungry\", what is the question?\n++++++++++\noutput: Why did Remy do this?\n\n\nPlease answer this: Sydney designed outfits to make for the new benefit show. Given that the answer to a question is \"Like she contributed\", what is the question?\n++++++++\nAnswer: How would Sydney feel afterwards?\n\n\nProblem: Aubrey saw that both kids wanted some of the only piece of fruit left, so she cut the apple in two. Given that the answer to a question is \"keeping the peace\", what is the question?\n\nA: How would you describe Aubrey?\n\n\nProblem: Given the question: Taylor sought an opportunity for Riley after he lost his job. Given that the answer to a question is \"know Riley before this\", what is the question?\n++++++++++++++++++++++++++++++++\nThe answer is:\nWhat does Taylor need to do before this?\n\n\nProblem: Alex got some new shoes at the mall. Alex wore their new shoes. Given that the answer to a question is \"excited by the new shoes\", what is the question?\n\nA:",
"role": "user"
},
{
"content": "How would you describe Alex?",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_88181
|
[
{
"content": "In this task, you are given triplets. Each triplet is in the form of [subject, predicate, object]. Your task is to generate proper sentence that utilizes these triples. The objective is to construct a sentence that (a) captures the facts specified in the triples and (b) is a well-formed sentence easily understandable by a human. All triple values need not be used directly in the sentence as long as the facts are adequately captured.\n\nInput: Consider Input: [['Akita Museum of Art', 'LOCATION', 'Akita, Akita'], ['Akita Prefecture', 'COUNTRY', 'Japan'], ['Akita, Akita', 'IS_PART_OF', 'Akita Prefecture']]\n\nOutput: Akita Museum of Art is located in Akita, Akita which is part of Akita Prefecture, Japan.\n\n\nInput: Consider Input: [['The Waterman', 'eatType', 'pub'], ['The Waterman', 'food', 'Fast food'], ['The Waterman', 'customer rating', 'low'], ['The Waterman', 'area', 'city centre']]\n\nOutput: There is Fast food pub with low customer rating, located in the city centre, named The Waterman.\n\n\nInput: Consider Input: [['The Vaults', 'eatType', 'coffee shop'], ['The Vaults', 'customer rating', '3 out of 5'], ['The Vaults', 'area', 'city centre'], ['The Vaults', 'near', 'Café Brazil']]\n\n",
"role": "user"
},
{
"content": "Output: The Vaults is a coffee shop with average pricing and a customer rating of 3 out of 5. It can be found in city centre near Café Brazil.\n\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_95492
|
[
{
"content": "QUESTION: Given the sentence \"The three people outside are waiting for a delivery.\" can we conclude that \"The people are waiting for car parts.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: Waiting for a delivery does not imply they are waiting for car parts.\nThe answer is it is not possible to tell.\n[QUESTION] Given the sentence \"A guy on a bike jumping from one large rock to another.\" can we conclude that \"A guy on a skateboard.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nHe refers to a guy on a bike not a guy on a skateboard.\nThe answer is no.\nQ: Premise: \"Two ladies wearing medical mask working in a food factory.\"\nBased on this premise, can we conclude that the hypothesis \"Two woman wearing masks are working.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: The woman in medical masks are working specifically in a food factory.\nThe answer is yes.\nQUESTION: Given the sentence \"A man with a bucket and a girl in a hat on the beach.\" can we conclude that \"The man and his girlfriend and looking for a quiet place on the beach to enjoy each other's company.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: Not every girl with a man is a girlfriend. Being on the beach together doesn't imply that two people are looking for a quiet place to enjoy each other's company.\nThe answer is it is not possible to tell.\n[QUESTION] Premise: \"A large crowd of protester are wearing jackets and carrying signs.\"\nHypothesis: \"The weather is cold.\"\nDo we know that the hypothesis entailed by the premise?\nJust because the protesters are wearing jackets doesn't necessarily mean it's cold.\nThe answer is it is not possible to tell.\nQ: If \"A couple crossing the street at night.\" does that mean that \"A couple crossing the street at night are on a date.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA:",
"role": "user"
},
{
"content": "Just cause they're a couple doesn't mean they're on a date.\nThe answer is it is not possible to tell.",
"role": "assistant"
}
] |
cot
|
cot_89539
|
[
{
"content": "QUESTION: Given the sentence \"The three people outside are waiting for a delivery.\" can we conclude that \"The people are waiting for car parts.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: Waiting for a delivery does not imply they are waiting for car parts.\nThe answer is it is not possible to tell.\n[QUESTION] Given the sentence \"A guy on a bike jumping from one large rock to another.\" can we conclude that \"A guy on a skateboard.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nHe refers to a guy on a bike not a guy on a skateboard.\nThe answer is no.\nQ: Premise: \"Two ladies wearing medical mask working in a food factory.\"\nBased on this premise, can we conclude that the hypothesis \"Two woman wearing masks are working.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: The woman in medical masks are working specifically in a food factory.\nThe answer is yes.\nQUESTION: Given the sentence \"A man with a bucket and a girl in a hat on the beach.\" can we conclude that \"The man and his girlfriend and looking for a quiet place on the beach to enjoy each other's company.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: Not every girl with a man is a girlfriend. Being on the beach together doesn't imply that two people are looking for a quiet place to enjoy each other's company.\nThe answer is it is not possible to tell.\n[QUESTION] Premise: \"A large crowd of protester are wearing jackets and carrying signs.\"\nHypothesis: \"The weather is cold.\"\nDo we know that the hypothesis entailed by the premise?\nJust because the protesters are wearing jackets doesn't necessarily mean it's cold.\nThe answer is it is not possible to tell.\nQ: If \"A couple crossing the street at night.\" does that mean that \"A couple crossing the street at night are on a date.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA:",
"role": "user"
},
{
"content": "Just cause they're a couple doesn't mean they're on a date.\nThe answer is it is not possible to tell.",
"role": "assistant"
}
] |
cot
|
cot_60527
|
[
{
"content": "[QUESTION] Premise: \"A man smiles and poses with a product he appears to be trying to sell.\"\nHypothesis: \"A person is posing with an object.\"\nDo we know that the hypothesis entailed by the premise?\nA product is an object so the words can be interchanged.\nThe answer is yes.\nQ: Given the sentence \"A man in sunglasses and a blue cap looking onward.\" is it true that \"A man never like blue cap.\"?\nA: A man who never like blue cap would not wear a blue cap.\nThe answer is no.\nQUESTION: If \"Children playing leapfrog beside fountain.\" does that mean that \"These children are all related.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: Children playing leapfrog beside fountain does not indicate that they are all related.\nThe answer is it is not possible to tell.\n[QUESTION] Given the sentence \"A man is standing in a park by a path holding a tennis racket in front of him.\" can we conclude that \"A man is standing in a park by a path holding a tennis racket ahead of him.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA tennis racket in front of him is the same as tennis racket ahead of him.\nThe answer is yes.\nQ: Premise: \"Two young men playing a game on rollerskates with curved sticks.\"\nBased on this premise, can we conclude that the hypothesis \"While a referee looks on.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: Two men are wearing roller skates while playing a game with sticks in their hands.\nThe answer is yes.\n[QUESTION] Given the sentence \"A man and woman sit on the floor with two children as one child reads a book and another opens a present.\" can we conclude that \"The woman is on the floor with children.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n",
"role": "user"
},
{
"content": "The woman is on the floor with children implies a woman and two children as one child reads a book and another opens a present.\nThe answer is yes.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_89183
|
[
{
"content": "In this task, you're shown a three-part story, with a beginning, middle, and ending. Your job is to slightly modify the middle part, so that the whole story becomes unlikely, improbable, or inconsistent. Generated sentences must minimally alter the given middle, with at most 4 new words added/existing words removed. Your sentence should be grammatically and syntactically correct. Also stick to the context of the given story. For example, if the story talks about \"doctors\", you can talk about \"health\" or \"diagnosis\", but don't mention \"aliens\". Avoid introducing any extra/irrelevant information, and use names instead of pronouns (e.g. he / she) wherever possible. Avoid simply negating the original middle, for example: \"She likes cakes.\" is changed to \"She doesn't like cakes.\"\n\nInput: Consider Input: Beginning: Cora and her friends were on a day trip. Middle: They decided to go swimming since I was sunny out. Ending: Cora and her friends had a great day at the beach!\n\nOutput: They decided to go movie watching since it was sunny out.\n\n\nInput: Consider Input: Beginning: Drew went to the grocery shop. Middle: He brought a sandwich, but it tasted bad. Ending: He immediately threw it away.\n\nOutput: Drew brought a sandwich, and it tasted great.\n\n\nInput: Consider Input: Beginning: Ai was a sheltered child who had been abused for years. Middle: Ai was best friends with the girl next door. Ending: And one day their mom found both little girls laughing together!\n\n",
"role": "user"
},
{
"content": "Output: Ai was best friends with an imaginary boy.\n\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_85658
|
[
{
"content": "TASK DEFINITION: In this task you are given a list of triplets of the form [subject, predicate, object] and the output should be a question based on the triplets but with the subject and/or object replaced with blanks (represented using two or more consecutive underscores). Triplet values encompassed in [*] are special tokens that can be replaced with synonyms. The objective is to construct a question in a manner that (a) captures the facts specified in at least one of the triplets, and (b) ideally contains a limited number of blanks such that it is a well-formed question that is easy to answer. A blank can represent a single word or a phrase.\nPROBLEM: [['[TABLECONTEXT]', '[TITLE]', 'List of NWA World Heavyweight Champions'], ['[TABLECONTEXT]', 'WRESTLER', 'Dan Severn'], ['Dan Severn', 'COMBINED_DAYS', '1,559']]\n\nSOLUTION: _____ was champion for _____ days.\n\nPROBLEM: [['The Rice Boat', 'eatType', 'restaurant'], ['The Rice Boat', 'food', 'Italian'], ['The Rice Boat', 'customer rating', '5 out of 5'], ['The Rice Boat', 'area', 'riverside'], ['The Rice Boat', 'familyFriendly', 'yes'], ['The Rice Boat', 'near', 'Express by Holiday Inn']]\n\nSOLUTION: The riverside Italian restaurant _____ is a family friendly restaurant conveniently located near the Express by Holiday Inn. The restaurant is rated 5 out of 5.\n\nPROBLEM: [['The Golden Curry', 'eatType', 'restaurant'], ['The Golden Curry', 'food', 'Italian'], ['The Golden Curry', 'customer rating', 'low'], ['The Golden Curry', 'area', 'city centre'], ['The Golden Curry', 'familyFriendly', 'no'], ['The Golden Curry', 'near', 'Café Rouge']]\n\nSOLUTION:",
"role": "user"
},
{
"content": "_____ is an Italian _____ near Café Rouge in City center that is not family-friendly and has a low rating.\n\n",
"role": "assistant"
}
] |
cot
|
cot_92101
|
[
{
"content": "Q: Given the sentence \"The photo has been edited to be black and white with splashes of color on the bikes.\" is it true that \"The band is back together.\"?\nA: A photo is not a band and does not constitute reunification.\nThe answer is no.\nQUESTION: Can we conclude from \"A street musician in bright red outfit plays his instrument.\" that \"A skate boarder is rolling down the hill.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\n\nLet's solve it slowly: A street musician playing his instrument and a skate boarder going down the hill are descriptions of two different people and activities.\nThe answer is no.\n[QUESTION] Premise: \"A golfer wearing a striped red polo shirt and white pants watches his drive after swinging.\"\nBased on this premise, can we conclude that the hypothesis \"A woman plays golf.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\nHis drive indicates the person is a man not a woman.\nThe answer is no.\nQ: Test for natural language inference.\nPremise: \"A man is playing a game with toy soldiers.\"\nHypothesis: \"A man is using figurines.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: A man is using figurines implies that he is playing a game.\nThe answer is yes.\nQUESTION: Test for natural language inference.\nPremise: \"Two men stand on a street in a city and the man on the right points at something.\"\nHypothesis: \"The man on the right points out a place to eat.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\n\nLet's solve it slowly: Not all men who points at something points out a place to eat.\nThe answer is it is not possible to tell.\nQUESTION: If \"A young woman is sitting on a rock bench and she is dressing in a bright pink and green striped sweater.\" does that mean that \"A women is sitting on a bench.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly:",
"role": "user"
},
{
"content": "A woman is part of description of a young woman sitting on a bench which is a rock bench.\nThe answer is yes.",
"role": "assistant"
}
] |
cot
|
cot_94127
|
[
{
"content": "question: Fill in the blank with the correct number in this number series: 1, 20, 7, 16, __, 12, 19, ?\nOptions:\n(A) 14\n(B) 12\n(C) 13\n(D) 15\n(E) 11\nanswer: Stream of consciousness: This is a simple alternating subtraction and addition series; The first series begins with 1 and adds 6; the second begins with 20 and subtracts 4, and so on. The answer is (C).\n--\nquestion: Find the odd man out? 3, 7, 15, 17, 22, 27, 29\nOptions:\n(A) 15\n(B) 17\n(C) 22\n(D) 27\n(E) 0\nanswer: Stream of consciousness: Each of the numbers is odd number except 22. The number 22 is the only even number. The answer is (C).\n--\nquestion: If a train, travelling at a speed of 90 kmph, crosses a pole in 5 sec, then the length of train is?\nOptions:\n(A) 125 m\n(B) 104 m\n(C) 140 m\n(D) 152 m\n(E) 150 m\nanswer: Stream of consciousness: D = 90 * 5/18 * 5 = 125 m The answer is (A).\n--\nquestion: Find the value of y from (12)^3 x 6^4÷432 =y?\nOptions:\n(A) 4363\n(B) 4765\n(C) 4879\n(D) 6789\n(E) 5184\nanswer:",
"role": "user"
},
{
"content": "Stream of consciousness: Given Exp. = (12)3 x 64 = (12)3 x 64 = (12)2 x 62 = (72)2 = 5184\n432 12 x 62 The answer is (E).\n--",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_83962
|
[
{
"content": "In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to return the position of all the numerical elements in the given list in order. Assume the position of the 1st element to be 1. Return -1 if no numerical element is in the list.\n\n[Q]: ['i', '7325', '6501', '1539']\n[A]: 2, 3, 4\n\n\n[Q]: ['r', '7805', 'F', 'j', '5531', '9917', 'T', 'c', 'q', '6469', 'O', '9423', '5459', '6261', '3845', 'f', '6139', '7877', 'o', 'X', '3741', '4623', '9801', 'M', '4513', 'C', 'E']\n[A]: 2, 5, 6, 10, 12, 13, 14, 15, 17, 18, 21, 22, 23, 25\n\n\n[Q]: ['3411', '9045', '2739', '9377', '5419', '5385', '1741', '8731', 'v', '6183', '4435', '8253', 'Z', 'u', 'T', 'g', 'o', '3153', '27', 'W', 'z', 'J']\n[A]:",
"role": "user"
},
{
"content": "1, 2, 3, 4, 5, 6, 7, 8, 10, 11, 12, 18, 19\n\n\n",
"role": "assistant"
}
] |
cot
|
cot_88400
|
[
{
"content": "Q: Given the sentence \"Green sunglasses and a pink swimsuit set the tone for stepping into the cold pool.\" is it true that \"Green sunglasses and a pink swimsuit is something that isn't being worn.\"?\nA: Setting the tone doesn't imply that something that isn't being worn.\nThe answer is no.\nQUESTION: Premise: \"A light colored dog with blue leash attached is sitting in a vehicle.\"\nHypothesis: \"A dog with a blue leash in a vehicle.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: A dog sitting in a vehicle is a rephrasing of a dog in a vehicle with an action verb.\nThe answer is yes.\n[QUESTION] Can we conclude from \"A little boy in a winnie the pooh t-shirt is waiting to swing his red bat.\" that \"A little boy in a winnie the pooh t-shirt is in a swimming pool.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nYou cannot be in a swimming pool and waiting to swing a red bat at the same time.\nThe answer is no.\nQ: Can we conclude from \"A group of musicians are performing on a stage in front of a crowd.\" that \"Musicians are on a stage.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: Musicians performing on a stage is another way of saying musicians are on a stage.\nThe answer is yes.\nQUESTION: If \"A dog swims.\" does that mean that \"There is a dog swimming in a lake.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: A dog swimming is not assumed to be in a lake.\nThe answer is it is not possible to tell.\nQUESTION: Test for natural language inference.\nPremise: \"Several soldiers dressed in green camouflaged uniforms are standing in front of a building.\"\nHypothesis: \"Lopsided men arm wrestling for universal champion as a volcano violently erupts behind them.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\n\nLet's solve it slowly:",
"role": "user"
},
{
"content": "The men cannot be wrestling and standing at the same time.\nThe answer is no.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_82299
|
[
{
"content": "Given the task definition, example input & output, solve the new input case.\nIn this task, you are given a text of many news articles seperated by special token \"|||||\". Your task is to summarize them.\nExample: A photo series on the popular Humans of New York Facebook page may have went viral and captured the nation’s attention last Tuesday, but for Daniel Kang, the post really hit home. \n \n When Kang, a junior studying computer science at the University of Michigan, heard that the refugee pictured and his family were relocating to his hometown of Troy, Mich., he said he knew he had to help. \n \n “I was really inspired by how intelligent he was and I knew a lot of people wanted to welcome him, so I thought, why not it be me?” he said. \n \n On the Humans of New York Facebook page with over 16 million likes — including comments from President Obama — the seven-part picture series’ captions detail one Syrian scientist and his family’s tale of loss after a missile strike destroyed their home, forcing them to to flee to Turkey, now with plans of coming to the United States. \n \n “Everything ended for us that day. That was our destiny. That was our share in life,” the scientist said. Battling stomach cancer, the loss of a home, career and seven family members, the man, whose name remains confidential to protect his identity as a refugee, expressed his hope for a new life in the United States. \n \n “I learned today that I’m going to Troy, Michigan,” he said. “I know nothing about it. I just hope that it’s safe and that it’s a place where they respect science. I just want to get back to work. I want to be a person again. I don’t want the world to think I’m over. I’m still here.” \n \n Knowing that refugees come to the United States with little more than they can carry, Kang quickly organized a crowdfunding campaign to help establish the man in his new home. \n \n In four days, the GoFundMe page has raised over $16K in donations from over 700 people. On Saturday afternoon, actor Edward Norton also began a fundraiser for the scientist, raising even more for the refugee who says he “just wants to be a person again.” \n \n “The response has been overwhelmingly positive,” said Kang. “A lot of people thanked me for doing a nice thing but I really feel like I was doing what anyone else would have done.” \n \n Kang said he’s received many messages from people expressing their gratitude, those who want to reach out to the man personally, as well local companies interested in working with the scientist. This includes invitations to lecture at local colleges, research job opportunities and potential help from local medical facilities in treating the man’s stomach cancer. \n \n “There’s definitely a lot of interest in helping him out,” he said. \n \n The biggest concern, said Kang, are those skeptical of how the money will reach the man. \n \n Kang, who has successfully crowdfunded in the past, is working closely with GoFundMe, the local refugee relocation agency Lutheran Social Services of Michigan, and is in communication with the Humans of New York staff to make sure all funding goes to the scientist. \n \n In the end, Kang said he just hopes the scientist receives the welcome he deserves. \n \n “If I could talk to him right now, I’d just tell him how sorry I am for everything he’s been through and that he’s coming to a great place. One of the things he said that resonated with me the most is that ‘I hope Troy is a place that appreciates science.’ \n \n I’d say out of all the cities in Michigan, Troy is the best place to raise a family, be a scientist and we can’t wait to have him.” \n \n Oona Goodin-Smith is a student at Oakland University and a member of the USA TODAY College contributor network. ||||| I saw this story on one of my favorite sites, Humans of New York, and it moved me to tears. This man has suffered profound loss that would crush the spirit of many people and yet he still passionately wants a chance to contribute positively to the world. If we don’t welcome people like this into our communities and empower his dream of making an impact with his life, then we’re not the country we tell ourselves we are. Let’s reject the 'anti-human’ voices that tell us to fear refugees and show this man and his family what Americans are really made of. Let’s show that a country built by the energy and dreams of immigrants still believes in brave people who come here with hope for better life. \n \n Everything we raise here will go to help this family so that the father can get the medical treatment he needs to live and pursue his work, and his family can build a new stable life after their tragedy, and…as the Scientist beautifully expresses…to support his dream of contributing to the world. \n \n Thanks to Humans of New York for sharing these stories. Thanks to the team at CrowdRise for putting this together and figuring out how to get even the credit card transaction fees covered so we can get the maximum to the family. \n \n Thanks to everyone who rallies together to create the power of the crowd. If enough of us kick in the price of two frappucinos, we can probably transform the experience of this family and show them that life can deliver healing and kindness, not just heartbreak. \n \n Thanks to Benevolent, all donations are tax-deductible. We will work with Benevolent to use all donated funds to help this family and will seek to use any excess or unused funds to help the other 11 profiled in the HONY ‘Syrian American’ series. \n \n Edward Norton ||||| DETROIT, MI -- Moved to tears by a Humans of New York feature on a Syrian refugee fleeing to Metro Detroit, Hollywood actor Edward Norton launched an online fundraiser that had raised nearly $450,000 for the widower and his four children as of Thursday afternoon. \n \n \"I didn't hear about it, but I want to thank him very much from the humanity perspective,\" the man told NBC News after hearing about the fundraiser's success. \"There are people outside who need that money much more than me.\" \n \n The man asked NBC to refer to him as \"Abu Ammar,\" a fake named used to protect his relatives who remain in Syria. He's known to many on the Internet simply as \"The Scientist,\" which is also his profession. \n \n The refugee's family was scheduled to arrive in Troy, a Detroit suburb, Thursday. He and four surviving children spent the last two years in Instanbul, Turkey. They fled civil-war-torn Syria after the man's wife and one of his daughters were killed in a missile attack on April 6, 2013. \n \n His is one of 12 families featured by Humans of New York and cleared to resettle in the U.S. \n \n \"I learned today that I'm going to Troy, Michigan,\" the man told Humans of New York. \"I know nothing about it. I just hope that it's safe and that it's a place where they respect science. I just want to get back to work. I want to be a person again. I don't want the world to think I'm over. I'm still here.\" \n \n The story made rounds throughout the Internet and even garnered a response from President Barack Obama's official Facebook page: \n \n As a husband and a father, I cannot even begin to imagine the loss you've endured. You and your family are an inspiration. I know that the great people of Michigan will embrace you with the compassion and support you deserve. Yes, you can still make a difference in the world, and we're proud that you'll pursue your dreams here. Welcome to your new home. You're part of what makes America great. \n \n ,Norton, known for his roles in movies like \"Fight Club\" and \"Birdman,\" wrote in the description of his online fundraiser: \n \n If we don't welcome people like this into our communities and empower his dream of making an impact with his life, then we're not the country we tell ourselves we are. Let's reject the 'anti-human' voices that tell us to fear refugees and show this man and his family what Americans are really made of. Let's show that a country built by the energy and dreams of immigrants still believes in brave people who come here with hope for better life. \n \n (6/7) “I had no problems before the bombing. I think the cancer came from my sadness and my stress. It’s in my... Posted by Humans of New York on Tuesday, December 8, 2015 ||||| ISTANBUL — The grieving refugee who touched hearts as \"The Scientist\" on the Humans of New York blog only mustered a brief smile when told that a Hollywood star had helped raise $450,000 for him. \n \n Hours before flying to Michigan to start a new life in the U.S. on Thursday, the cancer-stricken Syrian civil engineer glanced down. \n \n \"I didn't hear about it, but I want to thank him very much from the humanity perspective,\" he said after NBC News revealed the crowdfunding appeal. Oscar-nominated actor Edward Norton was moved to tears after reading the refugee's biography on the photography site last week and launched the fundraiser. \n \n \"There are people outside who need that money much more than me,\" The Scientist said, displaying the sort of compassion and humility that helped his story go viral. \n \n The Scientist, who asked NBC News to refer to him as \"Abu Ammar\" to protect family in Syria, said his life was shattered by a bomb that killed his wife and daughter just under three years ago. \n \n He was later diagnosed with stomach cancer, and has had to care for five remaining children. \n \n They include a teenage son, who is still reeling after watching his mother die, and a daughter who carries inside of her shrapnel from the attack on April 6, 2013. \n \n \"When a bomb drops you don't know where it comes from,\" he said. \"There is no question our lives changed after that ... 180 degrees. I am mentally tired, in overwhelming sadness.\" \n \n “ As long as there are good people in the world … then we can stop this bloodshed” \n \n On Thursday, Abu Ammar and four of his children flew to Troy, Michigan, as part of a United Nations refugee resettlement program. \n \n For about two years, the family had been living close to destitution in Turkey. But the drive to succeed still lingers, Abu Ammar said. \n \n \"I've had ambitions since I was a child, and right now I'm still that same child with the same ambitions,\" he said. \"But I still have a message — sometimes when I'm talking to myself I say, 'No, I'm not supposed to die. I need to live long enough to realize my message to humanity.'\" \n \n Abu Ammar's story on Humans of New York, a popular blog started in 2010 that spawned a bestselling book, prompted an outpouring of compassion. Even President Barack Obama contributed, calling Abu Ammar and his family an \"inspirations\" on HONY's Facebook page. \n \n \"Yes, you can still make a difference in the world, and we're proud that you'll pursue your dreams here.\" Obama wrote. \"Welcome to your new home. You're part of what makes America great.\" \n \n Last night President @BarackObama wrote a very sweet welcome note to the scientist in Tuesday's story. pic.twitter.com/ZGrn3gOdR7 — Brandon Stanton (@humansofny) December 10, 2015 \n \n Norton, who starred in \"Birdman,\" \"Fight Club\" and \"American History X,\" set out to help pay The Scientist's medical expenses. \n \n \"This man has suffered profound loss that would crush the spirit of many people and yet he still passionately wants a chance to contribute positively to the world,\" Norton wrote. \n \n The resettlement of Syrian and Muslim refugees in the United States is controversial, especially in the aftermath of attacks by Islamic extremists in Paris and San Bernardino. Some politicians — notably GOP presidential hopeful Donald Trump — have called for a ban on Muslims entering the country. \n \n Abu Ammar told NBC News he didn't know anything about the debate over Muslims and immigration raging in the U.S. He also didn't have a solution to the war raging in his home country. \n \n \"I don't like to get into politics because I am a man of science, and I can separate science and politics completely,\" he said. \"But as long as there are good people in the world, and everyone looks into his or her conscience, then we can stop this bloodshed.\" \n \n Abu Ammar added: \"No one benefits from people dying, and wars overall never benefit anybody — so let's hope God can help everyone and put out this fire.\" |||||\nOutput: A Syrian refugee whose moving story went viral earlier this month starts his new life in Troy, Michigan, on Thursday, NBC News reports. The refugee—who wants to keep his real name out of the media to protect family members still in Syria—is known as \"The Scientist\" on the blog Humans of New York, where he was first profiled. \"I learned today that I’m going to Troy, Michigan,\" The Scientist told HONY. \"I know nothing about it. I just hope that it’s safe and that it’s a place where they respect science.\" According to MLive, The Scientist left Syria in 2013 after a bomb killed his wife and one of his daughters. Since then, he's been diagnosed with stomach cancer and was barely scraping by in Turkey. Despite being \"in overwhelming sadness,\" he and his surviving children are hoping for a new start in the US, he tells NBC. Thanks to his story—which even got the attention of President Obama—The Scientist will have some help to get that new start. NBC reports actor Edward Norton was moved to tears after reading The Scientist's story and started a crowdfunding page that has raised nearly $450,000. \"I didn't hear about it, but I want to thank him very much from the humanity perspective,\" The Scientist says. \"There are people outside who need that money much more than me.\" A Michigan college student was also inspired to help after hearing The Scientist would be moving to his hometown, according to USA Today. His fundraising page has raised more than $16,000. \"I’d say out of all the cities in Michigan, Troy is the best place to raise a family, be a scientist, and we can’t wait to have him,\" Daniel Kang says.\nThis is a good example. The output correctly summarizes the articles.\n\nNew input case for you: UW researchers have conducted what is believed to be the first experiment to show that two brains can be directly linked, allowing one participant to guess correctly what the other is thinking. \n \n Brain scientists at the University of Washington have used an old-fashioned parlor game in a novel way to prove that two people’s brains can be linked across the Internet — an experiment that sounds like it was ripped from the pages of a science-fiction novel. \n \n The experiment is believed to be the first one to demonstrate that two brains can be directly linked to allow one participant to correctly guess what the other is thinking. \n \n Researchers say melding two minds has the potential for a vast range of applications. For example, it might allow for the transfer of information from a healthy one to a damaged one. Or it might allow an alert person to transmit that brain state to somebody who is sleepy, or struggling to pay attention. \n \n “What we wanted to establish is that it is possible to use this rudimentary brain-to-brain collaboration … to solve a common problem,” said Andrea Stocco, an assistant professor of psychology and a researcher at the Institute for Learning & Brain Sciences at the UW. \n \n The research was published Wednesday in the journal PLOS ONE. The brain-science investigations are funded by a $1 million grant from the W.M. Keck Foundation. \n \n Researchers used “20 Questions,” a popular guessing game in which one person thinks of an object and the other tries to guess what it is with a series of 20 or fewer questions that can only be answered “yes” or “no.” \n \n In the experiment, two participants played the game in rooms a mile apart on campus. One participant wore an electrode-studded cap connected to an electroencephalography (EEG) machine to pick up signals from the brain. \n \n The other wore a cap with a magnetic coil positioned over the part of the brain that controls the visual cortex. \n \n The player wearing the electrode cap picked an object, and the player wearing the electric coil used a computer mouse to select from a list of questions to get more information about the object. The electrode-capped player signaled to the questioner whether the answer to the question was “yes” or “no” simply by looking at a flashing light that indicated the answer. A “yes” sent a signal to the questioner; a “no” sent no signal at all. The signal was transmitted via the Internet. \n \n If the answer was yes, the brain activity in the first player’s brain delivered a signal to the electric coil worn by the second player, which translated into a visual interruption or flash of light known as a “phosphene.” \n \n Stocco said it took trial-and-error to position the magnetic coil so that it reliably transmitted a signal to the player asking the questions. And not everyone saw the same visual interruption. \n \n “I consistently saw lines,” Stocco said. “Some saw lightning bolts, blobs or shapes.” \n \n Stocco said the success of the experiment took researchers by surprise. \n \n “We knew in theory it could work,” he said. “We wanted to know how well it could work.” \n \n Subjects arrived at the correct answer in the “20 Questions” game 72 percent of the time; to do that, they answered more than 90 percent of the questions correctly. In other words, they saw the visual interruption, and interpreted it as a “yes.” \n \n Five sets of participants played 20 rounds of the game — a mixture of 10 real games and 10 control games, in which no visual signal was sent at all. Participants guessed the correct answer only 18 percent of the time in the control games. \n \n It’s not the first time Stocco and his fellow researchers have delivered a brain-to-brain signal over the Internet. Two years ago, Stocco and computer-science professor Rajesh Rao conducted an experiment in which Rao transmitted signals from his brain to Stocco, causing his finger to twitch, involuntarily. \n \n At the time, researchers said they believed it was the first time two human brains had been directly connected in this manner. However, some neuroscientists dismissed the experiment as a publicity stunt. \n \n In the finger-twitch experiment, Stocco was not consciously moving his digits, said Chantel Prat, researcher and faculty member at the brain science center. In the new experiment, the questioner “can actually consciously experience the information transfer.” The new experiment advances the science because “two people work together to problem solve,” she said. \n \n Stocco said researchers hope they’ll eventually be able to transmit more complex signals, such as shapes rather than simple flashes of light. \n \n In the 20 Questions experiment, “the brain is trying to make sense of a signal that normally doesn’t exist,” he said. “The brain is saying, ‘I don’t know what this thing is, but I think it’s a line.’ If we can control that with more precision, we could make a shape, or an object.” \n \n If scientists could figure out how to transmit shapes between two brains, it might eventually allow people to collaborate on problem-solving in a completely novel way, he said. \n \n Stocco said there are other applications for the science, too. \n \n For example, researchers know how to measure patterns of brain activity to tell whether somebody is paying attention. One day, scientists may be able to capture those brain patterns and transmit them to a person whose mind wanders, such as a student trying to overcome Attention Deficit Hyperactivity Disorder. \n \n Or perhaps one day, you could record the electrical impulses that pulse through your brain when you are at the peak of performance, and use that to wake up your brain at a later state, when your attention is flagging. \n \n “It could be a new frontier of self-help,” Stocco said. ||||| UW team links two human brains for question-and-answer experiment \n \n Deborah Bach News and Information \n \n Imagine a question-and-answer game played by two people who are not in the same place and not talking to each other. Round after round, one player asks a series of questions and accurately guesses the object the other is thinking about. \n \n Sci-fi? Mind-reading superpowers? Not quite. \n \n University of Washington researchers recently used a direct brain-to-brain connection to enable pairs of participants to play a question-and-answer game by transmitting signals from one brain to the other over the Internet. The experiment, detailed today in PLOS ONE, is thought to be the first to show that two brains can be directly linked to allow one person to guess what’s on another person’s mind. \n \n “This is the most complex brain-to-brain experiment, I think, that’s been done to date in humans,” said lead author Andrea Stocco , an assistant professor of psychology and a researcher at UW’s Institute for Learning & Brain Sciences . \n \n “It uses conscious experiences through signals that are experienced visually, and it requires two people to collaborate,” Stocco said. \n \n \n \n Here’s how it works: The first participant, or “respondent,” wears a cap connected to an electroencephalography (EEG) machine that records electrical brain activity. The respondent is shown an object (for example, a dog) on a computer screen, and the second participant, or “inquirer,” sees a list of possible objects and associated questions. With the click of a mouse, the inquirer sends a question and the respondent answers “yes” or “no” by focusing on one of two flashing LED lights attached to the monitor, which flash at different frequencies. \n \n A “no” or “yes” answer both send a signal to the inquirer via the Internet and activate a magnetic coil positioned behind the inquirer’s head. But only a “yes” answer generates a response intense enough to stimulate the visual cortex and cause the inquirer to see a flash of light known as a “ phosphene .” The phosphene — which might look like a blob, waves or a thin line — is created through a brief disruption in the visual field and tells the inquirer the answer is yes. Through answers to these simple yes or no questions, the inquirer identifies the correct item. \n \n The experiment was carried out in dark rooms in two UW labs located almost a mile apart and involved five pairs of participants, who played 20 rounds of the question-and-answer game. Each game had eight objects and three questions that would solve the game if answered correctly. The sessions were a random mixture of 10 real games and 10 control games that were structured the same way. \n \n The researchers took steps to ensure participants couldn’t use clues other than direct brain communication to complete the game. Inquirers wore earplugs so they couldn’t hear the different sounds produced by the varying stimulation intensities of the “yes” and “no” responses. Since noise travels through the skull bone, the researchers also changed the stimulation intensities slightly from game to game and randomly used three different intensities each for “yes” and “no” answers to further reduce the chance that sound could provide clues. \n \n The researchers also repositioned the coil on the inquirer’s head at the start of each game, but for the control games, added a plastic spacer undetectable to the participant that weakened the magnetic field enough to prevent the generation of phosphenes. Inquirers were not told whether they had correctly identified the items, and only the researcher on the respondent end knew whether each game was real or a control round. \n \n “We took many steps to make sure that people were not cheating,” Stocco said. \n \n Participants were able to guess the correct object in 72 percent of the real games, compared with just 18 percent of the control rounds. Incorrect guesses in the real games could be caused by several factors, the most likely being uncertainty about whether a phosphene had appeared. \n \n “They have to interpret something they’re seeing with their brains,” said co-author Chantel Prat , a faculty member at the Institute for Learning & Brain Sciences and a UW associate professor of psychology. “It’s not something they’ve ever seen before.” \n \n Errors can also result from respondents not knowing the answers to questions or focusing on both answers, or by the brain signal transmission being interrupted by hardware problems. \n \n “While the flashing lights are signals that we’re putting into the brain, those parts of the brain are doing a million other things at any given time too,” Prat said. \n \n The study builds on the UW team’s initial experiment in 2013, when it was the first to demonstrate a direct brain-to-brain connection between humans. Other scientists have connected the brains of rats and monkeys, and transmitted brain signals from a human to a rat, using electrodes inserted into animals’ brains. In the 2013 experiment, the UW team used noninvasive technology to send a person’s brain signals over the Internet to control the hand motions of another person. \n \n The experiment evolved out of research by co-author Rajesh Rao , a UW professor of computer science and engineering, on brain-computer interfaces that enable people to activate devices with their minds. In 2011, Rao began collaborating with Stocco and Prat to determine how to link two human brains together. \n \n In 2014, the researchers received a $1 million grant from the W.M. Keck Foundation that allowed them to broaden their experiments to decode more complex interactions and brain processes. They are now exploring the possibility of “brain tutoring,” transferring signals directly from healthy brains to ones that are developmentally impaired or impacted by external factors such as a stroke or accident, or simply to transfer knowledge from teacher to pupil. \n \n The team is also working on transmitting brain states — for example, sending signals from an alert person to a sleepy one, or from a focused student to one who has attention deficit hyperactivity disorder, or ADHD. \n \n “Imagine having someone with ADHD and a neurotypical student,” Prat said. “When the non-ADHD student is paying attention, the ADHD student’s brain gets put into a state of greater attention automatically.” \n \n Many technological advancements over the past century, from the telegraph to the Internet, were created to facilitate communication between people. The UW team’s work takes a different approach, using technology to strip away the need for such intermediaries. \n \n “Evolution has spent a colossal amount of time to find ways for us and other animals to take information out of our brains and communicate it to other animals in the forms of behavior, speech and so on,” Stocco said. “But it requires a translation. We can only communicate part of whatever our brain processes. \n \n “What we are doing is kind of reversing the process a step at a time by opening up this box and taking signals from the brain and with minimal translation, putting them back in another person’s brain,” he said. \n \n Other co-authors are UW computer science and neurobiology undergraduate student Darby Losey , UW bioengineering doctoral student Jeneva Cronin, UW bioengineering doctoral student Joseph Wu, and Justin Abernethy , a research assistant at the UW Institute for Learning & Brain Sciences. ||||| Abstract We present, to our knowledge, the first demonstration that a non-invasive brain-to-brain interface (BBI) can be used to allow one human to guess what is on the mind of another human through an interactive question-and-answering paradigm similar to the “20 Questions” game. As in previous non-invasive BBI studies in humans, our interface uses electroencephalography (EEG) to detect specific patterns of brain activity from one participant (the “respondent”), and transcranial magnetic stimulation (TMS) to deliver functionally-relevant information to the brain of a second participant (the “inquirer”). Our results extend previous BBI research by (1) using stimulation of the visual cortex to convey visual stimuli that are privately experienced and consciously perceived by the inquirer; (2) exploiting real-time rather than off-line communication of information from one brain to another; and (3) employing an interactive task, in which the inquirer and respondent must exchange information bi-directionally to collaboratively solve the task. The results demonstrate that using the BBI, ten participants (five inquirer-respondent pairs) can successfully identify a “mystery item” using a true/false question-answering protocol similar to the “20 Questions” game, with high levels of accuracy that are significantly greater than a control condition in which participants were connected through a sham BBI. \n \n Citation: Stocco A, Prat CS, Losey DM, Cronin JA, Wu J, Abernethy JA, et al. (2015) Playing 20 Questions with the Mind: Collaborative Problem Solving by Humans Using a Brain-to-Brain Interface. PLoS ONE 10(9): e0137303. https://doi.org/10.1371/journal.pone.0137303 Editor: Marco Iacoboni, UCLA, UNITED STATES Received: April 30, 2015; Accepted: August 16, 2015; Published: September 23, 2015 Copyright: © 2015 Stocco et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited Data Availability: Data are available from Dryad: doi:10.5061/dryad.g15k7. Funding: This research was funded by an award of the W. M. Keck Foundation (http://www.wmkeck.org/) to AS, CSP, and RPNR. Competing interests: The authors have declared that no competing interests exist. \n \n Introduction Direct brain-to-brain interfaces (BBIs) are technologies that combine neuroimaging and neurostimulation methods to exchange information between brains directly in neural code. In BBIs, specific content is extracted from the neural signals of a “sender” brain, digitized, and re-encoded in the form of induced neural activity in a “receiver” brain. BBIs have been recently demonstrated in both animal models [1–3] and humans [4–6]. While BBIs in humans offer advantages in terms of the range of tasks that can be accomplished and the complexity of information that can be transferred [7], constraints on the invasiveness of brain stimulation technologies in humans limit the possible BBI paradigms. As a result, all of the existing human BBIs have adopted two standard, non-invasive, and relatively safe technologies; electroencephalography (EEG [8]) to record brain activity, and transcranial magnetic stimulation (TMS [9]) to modulate neural activity. Using these two technologies, Rao and colleagues [5] were able to detect the intention of moving the right hand in a sender, and induce the intended movement in the right hand of a receiver, thus allowing the pair to jointly cooperate to solve a visuo-motor task. Grau and colleagues [6], on the other hand, were able to transfer information between pairs of participants in the form of neurally modulated visual percepts, which could be decoded as words by the receiver through a pre-arranged code. While both experiments served as important proofs of concept, they were also subject to a number of limitations. For example, in Rao and colleagues’ study [5], the participant at the receiver end of the BBI received a stimulus to the motor cortex, which produced the intended motor action but was not consciously processed by the participant. In other words, the receiver did not experience the desire to move his or her hand. Therefore, while the BBI allowed two participants to collaborate to achieve a common goal, it did not take full advantage of the receiver’s capacity for processing information. In Grau and colleagues’ experiment [6], the information transmitted to the receiver through the stimulation of visual processing areas resulted in the conscious perception of “phosphenes,” which are temporary visual percepts in the form of lines or spots. The conscious experience of phosphenes was interpreted as a binary signal and used to encode simple words with a code akin to the Morse code. This approach takes full advantage of the human capacity to consciously process information, but because their BBI was not intended to achieve a common goal between the two participants, it lacked the collaborative nature of Rao and colleagues’ task [5]. Also, differently than Rao’s study, Grau and colleagues adopted an off-line delivery mode, where the same signals from a single sender participant were recorded and later broadcast to different receivers. Finally, none of the previous studies had the two participants engage in collaborative and interactive problem solving, in which the receiver can transmit information back to the sender. Such a “closed-loop” interaction could represent a significant advance for the potential applications of human BBI technologies. We report results from a new experiment that overcomes the limitations of these previous studies by increasing both the complexity of the tasks performed with a non-invasive BBI in humans, and the quantity of information transferred between two brains. In our experiment, five pairs of participants played a shortened version of the popular “20 Questions” parlor game, in which a participant can ask up to 20 yes/no questions in order to figure out what object a second participant is thinking of. We chose this paradigm because it presents several important features that test the utility of a BBI, including the fact that it is collaborative, potentially open-ended, operates in real-time, and requires conscious processing of incoming information. To better reflect their roles in the collaborative question-answering task, we refer to the BBI sender as “Respondent”, and the BBI receiver as “Inquirer.” As illustrated in Fig 1, the inquirer and the respondent (physically located about 1 mile apart) interact using a web interface in conjunction with the brain-to-brain interface. The respondent first thinks of an object belonging to a specific category (for example, an animal, e.g., “dog”); the inquirer then uses the web interface to select a question for the respondent (using a computer mouse) from a list shown on the computer screen. A non-invasive BBI (shown in red in Fig 1) decodes the answer directly from the respondent’s brain signals and conveys the answer to the inquirer through stimulation. PPT PowerPoint slide \n \n PowerPoint slide PNG larger image \n \n larger image TIFF original image Download: Fig 1. Architecture of the BBI and “20 Questions” Experiment. In the experiment, two participants (an “inquirer” and a “respondent”) played a question-answering game similar to “20 Questions.” The respondent is given an object (e.g., “dog”) that is unknown to the inquirer and that the inquirer has to guess. The inquirer asks a question about the object by selecting a question (using a mouse) from questions displayed on a screen. The question is then presented visually to the respondent through a web interface. The respondent answers “Yes” or “No” directly through their brain signals by paying attention to one of two flashing LEDs (“Yes” = 13 Hz; “No” = 12 Hz). The BBI uses EEG to decode the respondent’s answer, and a TMS apparatus to convey the answer to the inquirer by generating a visual percept through stimulation for “Yes” and the absence of a percept for “No.” In the figure, the BBI system is highlighted in red. https://doi.org/10.1371/journal.pone.0137303.g001 The BBI was designed to detect visual information from the respondent’s EEG activity (specifically, whether the respondent was attending to the “Yes”-labelled flashing LED or the “No”-labeled flashing LED), and elicit a corresponding visual percept in the inquirer through transcranial magnetic stimulation of the visual areas in the occipital cortex. A number of precautions (see below) were taken to ensure that the inquirer did not receive any information about the answer from any source other than the BBI itself. To ensure the validity of these precautions, each experimental session consisted of 10 experimental games and 10 “control” games; during the control games, the BBI sounded and felt similar to the experimental trials but it did not stimulate the occipital cortex. The order of experimental/control games was randomized prior to the beginning of the experiment. Participants were told in advance about the presence of two conditions, but were not told which condition each game belonged to. \n \n Results and Discussion The efficacy of the proposed BBI was quantified using several measures. The most straightforward is the number of games in which the inquirer was successfully able to identify the object that the respondent was thinking of. On average, our five pairs of subjects were able to successfully guess the correct object in 72% of the games in the experimental condition using information available from the BBI, in contrast to only 18% successfully guessed during the control conditions. Because the distributions of correct guesses in both the experimental and control conditions were Normal (as assessed by the Shapiro-Wilk Normality test: W > 0.91, p > 0.48) and the two distributions had equal variances (Levene’s test: F(1, 8) = 0.07, p = 0.79), the difference between conditions was tested with a paired T-test. he difference between the experimental and control conditions was highly significant (paired t(4) = 13.50, p = 0.0002, Cohen’s d = 9.55). When examining the control condition, it is important to measure chance performance. Chance performance can be estimated in two ways, either by assuming a random inquirer who classifies the respondent’s answers as “Yes” or “No” with equal probability, or assuming an ideal inquirer who always classifies the respondent’s answers as “No” because no cortical input is received in the control condition. Because of the specific ways in which our lists and questions were constructed, both estimates yield the same chance performance of 12.5%. Statistical analysis revealed that performances of all participants were above chance in the experimental condition (single-sample t(4) = 8.97, p = 0.0008), but not in the control condition (single-sample t(4) = 0.78, p = 0.50; Fig 4A). PPT PowerPoint slide \n \n PowerPoint slide PNG larger image \n \n larger image TIFF original image Download: Fig 4. Different Measures of BBI Performance Across Conditions and Subjects. (A) Mean number of objects correctly guessed by the inquirer over 10 experimental (red) and 10 control trials (black) across 5 pairs of subjects; chance performance is 0.125 (dotted line); (B) Mean area under the ROC curves (see Fig 5, below); chance performance is 0.5 (dotted line); (C) Mean number of bits transferred during the experimental and control conditions, using the mutual information criterion; chance performance corresponds to 0 bits (dotted line). In all figures, the grey lines represent the five pairs of participants. Note that in (A), two pairs near the center of the plot had identical performance, giving the appearance of only four lines. https://doi.org/10.1371/journal.pone.0137303.g004 A more detailed way to examine our results is to analyze a BBI using signal detection theory, or equivalently, to treat the BBI as a classification problem. In this analysis, the signal (or, in classification terms, the label) is the true response to each question, and the prediction (or the class) is the inquirer’s understanding of the respondent’s answer. The performance of each pair can then be described using Receiver Operating Characteristic (ROC) analysis [18]. In ROC analysis, performance is represented as a point in the coordinate space defined by two axes representing the true positives rate and the false positives rate. In this space, an ideal classifier will occupy the upper-left corner of the plot, corresponding to 0% false positives and 100% true positives. A random classifier, by contrast, would occupy any of the positions along the upwards diagonal line, where for each proportion of true positives an equal amount of false positives occurs. For each pair in our experiments, we expect performance in the experimental condition to be near to the upper-left corner, and performance in the control condition to be near the diagonal line. Each pair’s performance can be further broken down into separate data points, one for the respondent (considering the true response as the ground truth and the output of the EEG detection as the prediction) and one for the inquirer (considering the TMS pulse as the ground truth and the inquirer’s decision as the prediction). Fig 5 plots each of these ROC points separately for each pair (Fig 5A) and for each participant within each pair (Fig 5B and 5C). PPT PowerPoint slide \n \n PowerPoint slide PNG larger image \n \n larger image TIFF original image Download: Fig 5. Performance of Each Pair of Subjects. Each plot illustrates the performance of pairs of subjects in terms of Receiver Operating Characteristic (ROC) for the experimental (red dots) and control (gray dots) games. The first plot (A) depicts the performance of each pair as whole while the other two plots represent the individual performances of respondents (B) and inquirers (C) in each pair. Overlapping points are indicated by darker shades of red or gray. https://doi.org/10.1371/journal.pone.0137303.g005 In the ROC plot, the performance associated with each point can be quantified as a single number, which represents the area of the polygon formed by connecting the point to the lower-left, lower-right, and upper-right corners of the plot, with coordinates (0, 0), (0, 1) and (1, 1), respectively [18]. This value is known as Area Under the Curve (AUC) and ranges from 1.0 (for an ideal classifier that recognizes all of the true positives without any false positives) to 0.5 (for a random classifier, where increasing the true positive rate produces an equivalent increase in the false positive rate [18]). Individual AUCs were calculated using ROCR package [19]. Since the distribution of AUC values was normally distributed (Shapiro-Wilk test, W > 0.84, p > 0.16) and had similar variance (Levene’s test, F(1, 8) = 0.05, p = 0.82) in both conditions, the data was analyzed with Student’s T-test. The mean raw AUC for the control condition was 0.54, a number that is not significantly different from that for chance (single-sample t(4) = 1.27, p = 0.27). On the other hand, the raw AUC for the experimental condition was 0.90, which is significantly larger than the AUCs for both the control condition (paired t(4) = 11.93, p = 0.0003, Cohen’s d = 8.44) and chance (single-sample t(4) = 13.43, p = 0.0001; see Fig 4B). In the ROC plot, the performance associated with each point can be quantified as a single number, which represents the area of the polygon formed by connecting the point to the lower-left, lower-right, and upper-right corners of the plot, with coordinates (0, 0), (0, 1) and (1, 1), respectively [18]. This value is known as Area Under the Curve (AUC) and ranges from 1.0 (for an ideal classifier that recognizes all of the true positives without any false positives) to 0.5 (for a random classifier, where increasing the true positive rate produces an equivalent increase in the false positive rate [18]). Individual AUCs were calculated using ROCR package [19]. Since the distribution of AUC values was normally distributed (Shapiro-Wilk test, W > 0.84, p > 0.16) and had similar variance (Levene’s test, F(1, 8) = 0.05, p = 0.82) in both conditions, the data was analyzed with Student’s T-test. The mean raw AUC for the control condition was 0.54, a number that is not significantly different from that for chance (single-sample t(4) = 1.27, p = 0.27). On the other hand, the raw AUC for the experimental condition was 0.90, which is significantly larger than the AUCs for both the control condition (paired t(4) = 11.93, p = 0.0003, Cohen’s d = 8.44) and chance (single-sample t(4) = 13.43, p = 0.0001; see Fig 4B). A final measure of interest is the number of bits that were successfully transferred between the respondent and the inquirer using the BBI. Because each answer of the respondent excludes half of the remaining options in the inquirer’s list, it theoretically conveys exactly one bit of information. Thus, information can be calculated as the sum of all the correct answers understood by the inquirer. This measure, however, might overestimate performance, as it does not account for the fact that negative answers are always correctly identified in the control conditions (that is, “0” bits are always transferred correctly), and that the distribution of the respondent’s answers might be skewed (i.e., there might be more negative answers than positive during the experimental conditions). A more conservative and precise measure is the Mutual Information (MI) between the ground-truth correct answers (considered as the input to the BBI) and the inquirer’s understanding of the received answers (the output of the BBI) [20]. MI can be calculated by first converting the set of correct answers and the inquirer’s responses into two binary vectors C and R, with every single answer c in C and r in R coded as 1 for “Yes” and “0” for “No”, and then using the following formula: MI was computed using the Infotheo package [21]. Because MI ranges between 0 and 1 and is calculated in natural logarithms, the actual number of bits transferred is calculated by first converting the MI value into the corresponding base two logarithm, and then multiplying it by the total number of answers given over the course of the experiment (in this case, 30). Because the distribution of MI values is inherently non-Normal (Shapiro-Wilk test, W = 0.78, p = 0.06), the raw data was square-root transformed before being analyzed. The transformed MI scores were more Normally distributed (Shapiro-Wilk test, W = 0.82, p = 0.12) and had comparable variances across conditions (Levene’s test, F(1,8) = 0.14, p = 0.71), thus fitting the requirements of Student’s T-test. In the experimental condition, the raw mean number of bits transferred was 16.02, which was significantly greater than the mean 1.16 bits transferred during the control condition (paired t(4) = 6.02, p = 0.004, Cohen’s d = 5.87 Fig 4C). The raw number of bits transferred in the experimental condition was also greater than chance, which, in the mutual information framework, corresponds to 0 bits (single-sample t(4) = 11.32, p = 0.0003). Contrastingly, the average of 1.16 bits transferred during the control condition was not significantly different than chance (single-sample t(4) = 1.88, p = 0.13). In summary, the different measures of BBI performance collectively demonstrate that the inquirers correctly identified the respondents’ answers during the experimental conditions, but performed at chance levels during the control games. These results have two implications. First, the success of the five pairs during the experimental condition confirms that the interactive BBI was successful and generalizable across different human subjects. Second, the fact that the pairs’ performance was at chance levels during the control condition implies that the communication between the two participants was relying specifically on the information provided by the direct brain-to-brain connection, rather than through other environmental or sensory cues. \n \n Conclusions This paper presents the successful demonstration of a new, non-invasive BBI in humans, which allowed pairs of participants to successfully collaborate and complete a series of question-and-answer games using information transferred between their brains. This BBI paradigm significantly extends and improves previous protocols in that (1) it involves the transfer of consciously perceived information in the form of phosphenes, (2) works in real-time, and (3) permits bidirectional information exchange between two participants. In this sense, this experiment represents a significant step forward towards the goal of creating BBIs with real-world applications. Because phosphenes are private to the receiver and can be perceived under a variety of conditions, or even while performing other actions, they represent a more versatile and interesting means of transferring information than the induced finger movements used in [5]. The amount of information transferred (as measured by the number of bits) in the current experiment is also significantly greater than that transferred in previous BBI experiments, e.g., close to 25 bits for one of the pairs (see Fig 4C) compared to a maximum of 13.4 bits in [5]. Finally, another strength of the current study is the enrollment of participants in terms of number and diversity. With ten total participants, this is the largest BBI experiment to date; while the number might seem small compared to more traditional EEG BCI studies, the reported effect sizes are considerable, with Cohen’s d values ranging from 5.87 to 9.55. As a comparison, these effect sizes would correspond to Pearson correlation coefficient values between 0.96 and 0.99. With such effect sizes, calculations suggest that between 3 and 4 pairs of subjects would already be sufficient to achieve a statistical power > 0.99 for significance thresholds of p < 0.05, therefore having less than 1% chance of incurring in Type II errors. Our sample size is therefore statistically adequate to support our conclusions. In addition, this is also the most diverse BBI experiment in terms of subject characteristics. For example, to our knowledge, this is the first human BBI experiment to include female participants. Thus, our results are encouraging in terms of their ability to demonstrate the generalizability of BBIs to the general population. The current experiment is not without limitations. The most obvious of these is that, as in previous BBI demonstrations, our paradigm does not transfer information better than would be expected with canonical means, such as when two individuals communicate verbally. For instance, it is reasonable to assume that any pair of our participants would be able to correctly guess the object in 100% of the games if they were given the possibility to communicate verbally. However, in circumstances including a non-verbal participant (e.g., an individual with Broca’s aphasia), or pairs of participants that do not speak the same language, it is highly likely that the BBI paradigm would outperform a canonical verbal protocol. Note that the count of correct final guesses greatly underestimates the performances of individual participants. This is for two reasons; first, all the answers in a game need to be correct for a correct guess of the chosen object; and second, the accuracy of a pair is the product of the accuracies of its two independent participants. When the accuracies of each respondent and inquirer in identifying each response are considered, the results are indeed impressive (93.5% and 94.0% accuracies, respectively), with two participants achieving a perfect score (Respondents 2 and 3, in the Experimental condition). These performances correspond to a decline of only about 6% from the levels assessed at the end of the training phase for the inquirers. This small decline can be explained by mental fatigue, which was likely induced by the length of the experimental sessions (approximately 2 hours for the respondents, and 2.5 hours for the inquirers) and the need for participants to fixate the screen for long periods of time. There is, in fact, experimental evidence suggesting that reduced attention has detrimental effects on both SSVEP detection [22] and phosphene perception [23]. A second limitation of our study is that, while the experimental paradigm as a whole allowed bi-directional transfer of information between the respondent and the inquirer, the BBI remained unidirectional, allowing only the transfer of information from the respondent to the inquirer. Fully bi-directional BBIs, if executed in real-time, require the integration of EEG and TMS technologies for each participant, and the development of tasks in which all of the relevant information can be transmitted solely using the BBI. A final limitation is that the code used herein to transmit information was relatively simple, essentially relying on the transmission of binary perceptual signals. None of these limitations is inherent to the technologies or paradigms we adopted for the BBI. For example, EEG and TMS [24], or alternately fMRI and TMS [25], can be used concurrently, thus enabling true bidirectional BBIs. We intend to investigate such BBIs in the future. Our current efforts are aimed at increasing the complexity of information transmitted through human BBIs, such as the transmission of affective states and other types of information that would be otherwise difficult to verbalize. Under these circumstances, larger amounts of information could potentially be transferred, and a BBI would confer a distinct advantage over canonical, symbolic means of communication. We see this as an exciting venue for future research. \n \n Acknowledgments The authors would like to thank Devapratim Sarma for his help in designing the real-time EEG data processing interface. \n \n Author Contributions Conceived and designed the experiments: AS CSP DML JAA JAC RPNR. Performed the experiments: AS DML JAA JAC. Analyzed the data: AS DML JAC. Contributed reagents/materials/analysis tools: AS CSP RPNR. Wrote the paper: AS CSP DML JAC RPNR. Designed and implemented the experimental software: JW. |||||\nOutput:",
"role": "user"
},
{
"content": "University of Washington scientists say they pulled off the amazing feat of linking two minds over the Internet—and they didn't have to stick electrodes into anybody's brain to do it. Instead, pairs of study participants a mile apart wore caps—one connected to an EEG machine monitoring brain activity, the other connected to a magnetic coil capable of stimulating the visual cortex—to play a game of \"20 Questions,\" the Seattle Times reports. The researchers, whose study is published in the journal PLoS One, say that when the player with the coil used selected questions about an object from a list using a mouse, the player with the EEG cap was able to communicate a \"yes\" or \"no\" by focusing on a light, causing the other player to see a flash of light when the answer was \"yes.\" The researchers say the subjects determined the correct object in 72% of the \"mind meld\" games and in just 18% of control rounds. \"This is the most complex brain-to-brain experiment, I think, that's been done to date in humans,\" the lead researcher says in a university press release. \"It uses conscious experiences through signals that are experienced visually, and it requires two people to collaborate.\" The researchers say the project could be a gigantic breakthrough for communications, and they're working on ways to transmit brain states, which could transform a weary or distracted brain into an alert one. (Another study found that climbing a tree is great for your brain, even if you're in your 50s.)",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_82583
|
[
{
"content": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nIn this task, you are given a natural language interpretation of commands (consist of logical operations) to select relevant rows from the given table. Your job is to generate command (in terms of logical operations) from given natural language interpretation. Define body (contains a collection of statements that define what the this logical operator does) of each logical operator between '{}' parenthesis. Here are the definitions of logical operators that you can use while generating command: \n 1. count: returns the number of rows in the view. \n 2. only: returns whether there is exactly one row in the view. \n 3. hop: returns the value under the header column of the row. \n 4. and: returns the boolean operation result of two arguments. \n 5. max/min/avg/sum: returns the max/min/average/sum of the values under the header column. \n 6. nth_max/nth_min: returns the n-th max/n-th min of the values under the header column. \n 7. argmax/argmin: returns the row with the max/min value in header column. \n 8. nth_argmax/nth_argmin: returns the row with the n-th max/min value in header column. \n 9. eq/not_eq: returns if the two arguments are equal. \n 10. round_eq: returns if the two arguments are roughly equal under certain tolerance. \n 11. greater/less: returns if the first argument is greater/less than the second argument. \n 12. diff: returns the difference between two arguments. \n 13. filter_eq/ filter_not_eq: returns the subview whose values under the header column is equal/not equal to the third argument. \n 14. filter_greater/filter_less: returns the subview whose values under the header column is greater/less than the third argument. \n 15. filter_greater_eq /filter_less_eq: returns the subview whose values under the header column is greater/less or equal than the third argument. \n 16. filter_all: returns the view itself for the case of describing the whole table \n 17. all_eq/not_eq: returns whether all the values under the header column are equal/not equal to the third argument. \n 18. all_greater/less: returns whether all the values under the header column are greater/less than the third argument. \n 19. all_greater_eq/less_eq: returns whether all the values under the header column are greater/less or equal to the third argument. \n 20. most_eq/not_eq: returns whether most of the values under the header column are equal/not equal to the third argument. \n 21. most_greater/less: returns whether most of the values under the header column are greater/less than the third argument. \n 22. most_greater_eq/less_eq: returns whether most of the values under the header column are greater/less or equal to the third argument.\n\nselect the row whose attendance record of all rows is 3rd maximum. the competition record of this row is danish superliga 2005-06.\nSolution: eq { hop { nth_argmax { all_rows ; attendance ; 3 } ; competition } ; danish superliga 2005 - 06 }\nWhy? Here, the generated command using logical operators correctly selects third maximum from given table rows which is mentioned in natural language interpretation.\n\nNew input: for the date records of all rows , all of them fuzzily match to 9 june 1928 .\nSolution:",
"role": "user"
},
{
"content": "all_eq { all_rows ; date ; 9 june 1928 }",
"role": "assistant"
}
] |
cot
|
cot_80615
|
[
{
"content": "QUESTION: Given the sentence \"Chinese workers are working at a factory.\" can we conclude that \"People have lunch in an empty gymnasium.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: Working and having lunch are two different things and factory is not an empty gymnasium.\nThe answer is no.\n[QUESTION] Can we conclude from \"A man in a yellow shirt and light colored pants sits next to a woman wearing a light colored hat in front of a camper while a young boy in a yellow shirt and jeans tosses rocks.\" that \"A boy plays a game.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nWhena boy plays a game he may or may not tosses rocks.\nThe answer is it is not possible to tell.\nQ: Given the sentence \"Three dogs play near the water.\" is it true that \"Three dogs play on the stairs.\"?\nA: Dogs are either near the water or on the stairs but not both at the same time.\nThe answer is no.\nQUESTION: Premise: \"Four friends in a street.\"\nHypothesis: \"There are four friends.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: There are four friends because the four friends are in a street.\nThe answer is yes.\n[QUESTION] Given the sentence \"The girls were in the crowd.\" is it true that \"The girls waited anxiously in the crowd.\"?\nGirls in a crowd are not assumed to have waited anxiously.\nThe answer is it is not possible to tell.\nQ: Premise: \"An audience listens to a musical ensemble play in front of a pipe organ in an ornate performance hall.\"\nHypothesis: \"The audience is watching a play.\"\nDo we know that the hypothesis entailed by the premise?\nA:",
"role": "user"
},
{
"content": "Watching a play varies from listening to it by the audience.\nThe answer is no.",
"role": "assistant"
}
] |
cot
|
cot_63749
|
[
{
"content": "**Q**\nYes / no, is the following a verifiable fact?\n\"THE MEMBERS OF THE Bridgwater S ARE MONMOUTH REBELLION.\"\n**A**\nyes\nTHE DUKE OF MONMOUTH HAD BEEN POPULAR IN THE SOUTH WEST OF ENGLAND.\n\"Seismology deals with the study of stars and their orbits.\"\nIs the above claim true?\nOptions:\n- yes\n- no\nno\nIt is concerned with the study of earthquakes and similar environmental effects.\n**Q**\nDoes the following sentence make sense?\n\"Only few world's major faiths leaders, of count 10, signed the Initial Declaration of Golden Rule.\"\nOptions:\n- yes\n- no\n**A**\nno\nThe Initial Declaration was signed by 143 leaders from all of the world's major faiths, including Baháʼí Faith, Brahmanism, Brahma Kumaris, Buddhism, Christianity, Hinduism, Indigenous, Interfaith, Islam, Jainism, Judaism, Native American, Neo-Pagan, Sikhism, Taoism, Theosophist, Unitarian Universalist and Zoroastrian.\nClaim: \"Rodney King identifies an induvial who was attacked by the Los Angeles police department.\"\nIs the claim above correct, and can it be verified by human common sense and without a web search?\nOptions:\n- yes\n- no\nyes\nRodney King is an American political figure, and inspiration for many.\n**Q**\nIs the following statement true?\n\"Malcolm X fought for African-American civil rights.\"\n**A**\nyes\nMalcolm X was a civil rights activist during his life.\n**Q**\nIs the following statement true?\n\"Be careful eating Breadfruit, it can cause major stomach problems.\"\n**A**\n",
"role": "user"
},
{
"content": "no\nIf it is a staple food, I doubt it is associated with stomach problems.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_83044
|
[
{
"content": "TASK DEFINITION: In this task, you will be shown a conversation and a question. You need to answer the question and choose the correct option based on the conversation. \"W\" and \"M\" in the conversations stand for \"woman\" and \"man\".\nPROBLEM: W: Robert, you play the guitar, don't you? M: I used to. But I haven't played it for quite some time. I don't really have time these days with all my studies. Why do you ask? W: I'm trying to organize a group to play at some parties on weekends. We still need a guitar player. M: Well, I don't know. But your idea sounds fun to me. W: Oh, it will be. I'm more or less in charge of things, so if you want to give it a try, you're in. It's as easy as that. Besides, it's a great chance to get out to meet people. M: But I told you I haven't practiced for a long time. I don't know if I remember any songs I used to play. W: Don't worry about it. I just thought I'd ask you to try and join us sometime when we were practicing. We'll be practicing for a few months before we give performances. M: OK, I'll have a try. W: I'm sure you can do it. And it will be fun, too., Question: Why is Robert not sure of joining the group? (A) He doesn't think he is good enough. (B) He doesn't have time to practice. (C) He isn't interested in joining it.\n\nSOLUTION: (B) He doesn't have time to practice.\n\nPROBLEM: Receptionist: Dr. Carter's Office. Ronald: Yes, I'd like to make an appointment to see Dr. Carter, please. Receptionist: Is this your first visit? Ronald: Yes it is. Receptionist: Okay. Could I have your name please? Ronald: Yes. My name is Ronald Schuller. Receptionist: And may I ask who referred you to our office? Ronald: Uh, I drove past your office yesterday. Receptionist: Okay. How about the day after tomorrow on Wednesday at 4:00 O'clock? Ronald: Uh. Do you happen to have an opening in the morning? I usually pick up my kids from school around that time. Receptionist: Okay. Um ... how about Tuesday at 8:00 A.M. or Thursday at 8:15 A.M.? Ronald: Uh, do you have anything earlier, like 7:30? Receptionist: No. I'm sorry. Ronald: Well, in that case, Thursday would be fine. Receptionist: Okay. Could I have your phone number please? Ronald: It's 643-0547. Receptionist: Alright. And what's the nature of your visit? Ronald: Uh ... Receptionist: Yes sir. Ronald: Well, to tell the truth, I fell from a ladder two days ago while painting my house, and I sprained my ankle when my foot landed in a paint can. I suffered a few scratches on my hands and knees, but I'm most concerned that the swelling in my ankle hasn't gone down yet. Receptionist: Well, did you put ice on it immediately after this happened? Ronald: Well yeah. I just filled the paint can with ice and ... Receptionist: And so after you removed the paint can ... Sir, sir, Mr. Schuller, are you still there? Ronald: Well that's part of the problem. Uh, the paint can is still on my foot. Receptionist: Look, Mr. Schuller. Please come in today. I don't think your case can wait., Question: What is the man's name? (A) Russell (B) Randall (C) Ronald\n\nSOLUTION: (C) Ronald\n\nPROBLEM: M: Alice, do you know who's going to be in charge of the party, Mary or Jane? F: Neither Mary nor Jane is, the teacher has asked me to be in charge of it., Question: Who's going to be in charge of the party? (A) Alice (B) Mary (C) Jane\n\nSOLUTION:",
"role": "user"
},
{
"content": "(A) Alice\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_83713
|
[
{
"content": "In this task, you're given the title and three arbitrary sentences out of a five-sentence story. You are also given three additional sentence options, a, b, and c, that may or may not belong to the story. Your job is to pick the two options that seamlessly connect with the rest of the story; note that the selected choices may fit into the story at any point. Indicate your selected choices in order, i.e., as 'ab'/'bc'/'ac' and not as 'ba'/'ca'/'cb'. If options are equally plausible, pick the ones that make more sense.\n\nExample Input: Title: Ryan complained about his school schedule being ruined. However, Ryan did poorly on his classes throughout the semester. He ended up repeating the entire year since he failed. Choices: a. He visited the guidance counselor on the first day. b. His friends got mad. c. She managed to change his schedule.\nExample Output: ac\n\nExample Input: Title: Jimmy needed a new computer so he ordered one online. Jimmy saw the mailman carrying his new computer to the door. Jimmy set up his new computer and started to go to work. Choices: a. They knew the judges had done a good job. b. Jimmy was a poor kid who worked online. c. He waited very eagerly for the package to arrive.\nExample Output: bc\n\nExample Input: Title: He calls up some friends to play a game of poker. Johnson and his friends play all afternoon. He is glad he found something to do today. Choices: a. They all have a great time. b. She ended up getting a pop. c. Johnson is feeling bored one day.\nExample Output:",
"role": "user"
},
{
"content": "ac\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_87668
|
[
{
"content": "TASK DEFINITION: In this task, you're given a short story of five sentences written in natural language. However, the order of the given story is not correct. Your job is to return the correct order for the given five sentences to create a coherent short story with the new order that has the correct flow. Generate your answer using the number of sentences in the correct order, such as '23415'.\nPROBLEM: Sentence1: Lisa began to realize that she did not enjoy studying business. Sentence2: She wanted to study art but was worried about making money. Sentence3: Finally, one day she had the courage to drop out of school. Sentence4: Lisa still felt confident that her choice would make her happy. Sentence5: Her friends and family told her it was crazy to leave school.\n\nSOLUTION: 12354\n\nPROBLEM: Sentence1: They chose an action movie that had both comedic and thrilling parts. Sentence2: Janie wanted to see a comedy, but Lynne wanted to see a thrill. Sentence3: They were both happy. Sentence4: When they got to the movie theater, they decided to make a compromise. Sentence5: Janey and Lynne decided to go to the movies.\n\nSOLUTION: 42531\n\nPROBLEM: Sentence1: He was at the Salt Lake Airport with his family and saw his hero. Sentence2: Jamal Lewis gave him personal advice and wished him the best. Sentence3: Young Reggie loved playing and watching american football. Sentence4: His favorite player was running back Jamal Lewis. Sentence5: He went up to him saying that he will also play professional football.\n\nSOLUTION:",
"role": "user"
},
{
"content": "35124\n\n",
"role": "assistant"
}
] |
cot
|
cot_71750
|
[
{
"content": "QUESTION: Given the sentence \"A little girl eats an apple and sits in front of a map of the world.\" is it true that \"The girl is playing in the ocean.\"?\n\nLet's solve it slowly: The girl can't be playing in the ocean while she eats an apple.\nThe answer is no.\n[QUESTION] If \"A small black dog is standing over a small white dog laying on his side.\" does that mean that \"A mother dog is caring for her pup.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA black dog standing over a small dog laying on his side is not necessarily a mother dog caring for her pup.\nThe answer is it is not possible to tell.\nQ: Can we conclude from \"A black dog pulling on a green rope in the grass.\" that \"A dog is in the park.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: A dog in the grass does not have to be in the park.\nThe answer is it is not possible to tell.\nQUESTION: Given the sentence \"A group of soldiers are standing with guns in front of an armored vehicle.\" is it true that \"A group of soldiers are standing with guns in front of vehicles to pose for marketing photos.\"?\n\nLet's solve it slowly: Standing with guns does not imply to pose for marketing photos.\nThe answer is it is not possible to tell.\n[QUESTION] Premise: \"Two smiling little girls in a boat on a lake are hugging.\"\nHypothesis: \"Two girls are fishing.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- it is not possible to tell\n- no\nHugging is not an activity that can be done simultaneously while fishing.\nThe answer is no.\nQ: Premise: \"Two parasailors on one parasail landing on a sandy beach in front of a large rocky boulder and the water.\"\nBased on this premise, can we conclude that the hypothesis \"There are two parasailors who will land on the beach.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA:",
"role": "user"
},
{
"content": "To be landing on a sandy beach it is implied they will land.\nThe answer is yes.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_15536
|
[
{
"content": "How is \"New Woman\" said in Russian?\nНовая женщина\n\n\nQ: Translate \"Першим кроком повинен стати скликання Всенародних зборів, на яких громадяни закріплять своїми рішеннями реалізацію наміченого плану по встановленню контролю над владою, запустять процес очищення й легітимізації влади.\" to Russian?\n\nA: Первым шагом должен стать созыв Всенародного собрания, на котором граждане закрепят своими решениями реализацию намеченного плана по установлению контроля над властью, запустят процесс очищения и легитимизации власти.\n\n\ninput question: Write a sentence not in English.\noutput answer: Хамза\n\n\nQ: Translate \"It is Maria Theresa -- a name of which there is not a single trace in either of the three documents.\"\" to Russian?\nYes: Это остров Мария-Тереза, но нет никаких следов этого названия ни в одном из трех документов.\n\n\n[Q]: Не мудрено: у него есть свой метод: прагматизм.\n\nTranslate this to English?\n[A]: This is not surprising: he possesses a method - pragmatism.\n\n\nHow is \"If you find no keyword pages or sub-categories that relate to your content, you can suggest and create your own keyword pages or sub-categories that relate to \"...careers...\" and then you can add your contextual listings there, free and in real time.\" said in Russian?\n",
"role": "user"
},
{
"content": "Если не находишь страницы с ключевыми словами или подкатегории, относящиеся к текстам на твоей странице, можешь предложить и создать свои собственные страницы с ключевыми словами или подкатегории связанные с \"...careers...\" и можешь добавить свои контекстуальные листинги там, бесплатно и в реальное время.",
"role": "assistant"
}
] |
cot
|
cot_75526
|
[
{
"content": "Q: Given the sentence \"There is a statue on the side of a building.\" is it true that \"There is a statue of a building.\"?\nA: yes\nCoT: There is a statue of a building because there is a statue on the side of the building.\n****\nQ: Test for natural language inference.\nPremise: \"Person holding a frisbee with a white dog jumping for it on a road.\"\nHypothesis: \"A man is playing with his dog.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: it is not possible to tell\nCoT: A man throwing a frisbee to a dog doesn't necessary mean that the dog is his.\n****\nQ: Test for natural language inference.\nPremise: \"A man with a blue polo is standing in front of a taxi.\"\nHypothesis: \"A naked man is standing in front of a taxi.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: no\nCoT: A man cannot wear a blue polo and be naked at the same time.\n****\nQ: Test for natural language inference.\nPremise: \"Two crew members are on the deck of the boat.\"\nHypothesis: \"Two crew members on the boat deck.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: yes\nCoT:",
"role": "user"
},
{
"content": "The deck of the boat is another way to say boat deck.\n****",
"role": "assistant"
}
] |
cot
|
cot_52970
|
[
{
"content": "QUESTION: Given the sentence \"An antique car that is yellow is shown lined up with other cars.\" can we conclude that \"Cars were made last year.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: An antique car is older than a car from last year.\nThe answer is no.\n[QUESTION] Given the sentence \"A man wearing a blue hooded sweatshirt hangs from a window pulley up in the air while next to a white building.\" can we conclude that \"The man in the sweatshirt is hanging outside of the building.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nIf a man hangs from a window pulley up in the air then he is hanging outside of the building.\nThe answer is yes.\nQ: Given the sentence \"Culinary judge announces as he opens dish.\" is it true that \"The judge announces the tv show.\"?\nA: Person cannot simultaneously announces something about the dish and the tv show.\nThe answer is no.\nQUESTION: Premise: \"A white dog wearing a christmas reindeer headband plays with a brown dog in the grass among some stuffed animals.\"\nHypothesis: \"Two dogs are playing dressed up for halloween.\"\nDo we know that the hypothesis entailed by the premise?\n\nLet's solve it slowly: If you are dressed up for Christmas you cannot be simultaneously dressed up for Halloween.\nThe answer is no.\n[QUESTION] Premise: \"A man with a hiking backpack on is standing in front of a lake with a forest in the background.\"\nHypothesis: \"A man is hiking for his dead wife.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA hiker standing in front of a lake does not imply he is hiking for his dead wife.\nThe answer is it is not possible to tell.\nQ: Premise: \"A man looking to purchase ice cream from and ice cream truck at night.\"\nHypothesis: \"The man wants some icecream.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA:",
"role": "user"
},
{
"content": "A man looking to purchase ice cream shows that he wants some icecream.\nThe answer is yes.",
"role": "assistant"
}
] |
cot
|
cot_63665
|
[
{
"content": "A family enjoying a day at the park do just that.\nThe question and answer are below.\nGiven the sentence \"Family members enjoying a beautiful sunny day at the park.\" can we conclude that \"A family enjoying a day at the pak.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nyes\n\nA man wearing a bib with a red crab on it is not necessarily at Red Lobster.\nThe question and answer are below.\nCan we conclude from \"A man wearing a bib with a red crab on it is trying to decide if he wants to eat a boiled crab.\" that \"The man is at red lobster.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nit is not possible to tell\n\nA man drilling into a building can be making a hone and not necessarily putting siding.. So what could be the question?\nQuestion followed by answer: Test for natural language inference.\nPremise: \"A man in a hooded sweatshirt is on a ladder drilling into a building while three people watch him.\"\nHypothesis: \"The mad is putting siding on the house.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nit is not possible to tell\n\nJust because flaggers are chatting on a construction site doesn't imply they are waiting for traffic to direct.\nThe question and answer are below.\nPremise: \"Two flaggers chatting on a construction site.\"\nHypothesis: \"The flaggers are waiting for traffic to direct.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- it is not possible to tell\n- no\nit is not possible to tell\n\nIf it is in the sky it's above them. One man and one woman is people. If they peer at something they are looking at it.\nThe question and answer are below.\nPremise: \"An old man and woman peer at something in the sky.\"\nHypothesis: \"Two people have their attention on something above them.\"\nDo we know that the hypothesis entailed by the premise?\nyes\n\nBoys waving green and blue striped flags in unison are not necessarily celebrating their team winning the game.\nThe question and answer are below.\n",
"role": "user"
},
{
"content": "Given the sentence \"Boys in bright green pants and dark green shirts run in circles waving green and blue striped flags in unison.\" is it true that \"A couple boys are celebrating their team winning the game.\"?\nit is not possible to tell",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_91395
|
[
{
"content": "TASK DEFINITION: You are given a statement written in Kannada. Choose the most logical word from the given 4 options which can be used to replace the <MASK> token in the statement. Output the word from the correct option .\nPROBLEM: Statement: ಕೇಂದ್ರ ಸರ್ಕಾರ ಜೂನ್ 1999 ರಲ್ಲಿ ಭಾರತೀಯ ಸೇನೆಗೆ ಒಳನುಸುಳುಕೋರರನ್ನು ಪ್ರತಿರೋಧಿಸಲು ಆಪರೇಷನ್ ವಿಜಯ್ ಹೆಸರಿನ ಯುದ್ಧ ಆರಂಭಿಸುವಂತೆ ಅಪ್ಪಣೆ ಕೊಟ್ಟಿತು. ಕಾಶ್ಮೀರ ಗಡಿಯಲ್ಲಿನ ತೀವ್ರ ಕಡಿಮೆ ತಾಪಮಾನ, ವಿರೋಧಿ ಬಣದಿಂದ ಮಳೆಯಂತೆ ಬಂದು ಸುರಿಯುತ್ತಿದ್ದ ಗ್ರೆನೇಡುಗಳು, ಸಮುದ್ರ ಮಟ್ಟದಿಂದ ಅತೀ ಎತ್ತರದಲ್ಲಿದ್ದು ಆಗಾಗ ಉಸಿರಾಡಲೂ ಕಷ್ಟವಾಗುವಂತಹ ಕ್ಲಿಷ್ಟ ಪರಿಸ್ಥಿತಿಗಳಲ್ಲಿ ಭಾರತೀಯ ಯೋಧರು <MASK>ಕ್ಕೆ ಎದಿರೇಟು ಕೊಡುವಲ್ಲಿ ಸಫಲರಾಗುತ್ತಿದ್ದರು. * ಮೂರು ತಿಂಗಳ ಪರ್ಯಂತ ನಡೆದ ಕಾರ್ಗಿಲ್ ಯುದ್ಧದಲ್ಲಿ ೫೨೭ ಜನ ಭಾರತೀಯ ಯೋಧರು ಹುತಾತ್ಮರಾದರು ಹಾಗೂ ಪಾಕಿಸ್ತಾನ ಬಣದಲ್ಲಿ ಸುಮಾರು ೬೦೦-೪೦೦೦ ಸೈನಿಕರು ಹತರಾಗಿರುವ ಬಗ್ಗೆ ಅಂದಾಜಿಸಲಾಗಿದೆ.\n\n Option A: ಪಾಕಿಸ್ತಾನ\n\n Option B: ಭಾರತ\n\n Option C: ಲೋಕಸಭೆ\n\n Option D: ಪ್ರಧಾನಮಂತ್ರಿ\n\nSOLUTION: ಪಾಕಿಸ್ತಾನ\n\nPROBLEM: Statement: ಕೇದಾರ ರವರು ಮಾರ್ಚ್ ೨೬, ೧೯೮೫ರಲ್ಲಿ <MASK>ದ ಪುಣೆಯಲ್ಲಿ ಜನಿಸಿದರು.ನಾಲ್ಕು ಮಕ್ಕಳಲ್ಲಿ ಇವರು ಕಿರಿಯವರು. ತಂದೆ ಮಹಾದೇವ್ ಜಾಧವ್ ಮಹಾರಾಷ್ಟ್ರದ ವಿದ್ಯತ್ ಮಂಡಳಿಯಲ್ಲಿ ಗುಮಾಸ್ತರಾಗಿದ್ದರು. ಕೇದಾರ್ ರವರು ೨೦೦೪ರಲ್ಲಿ ಮಹಾರಾಷ್ಟ್ರದ ೧೯ರ ವಯ್ಯೋಮಿತಿ ತಂಡಕ್ಕೆ ಆಯ್ಕೆ ಆದರು.\n\n Option A: ಭಾರತ\n\n Option B: ಲ್ಯಾಟ್ವಿಯ\n\n Option C: ಜಿಂಬಾಬ್ವೆ\n\n Option D: ಮಹಾರಾಷ್ಟ್ರ\n\nSOLUTION: ಮಹಾರಾಷ್ಟ್ರ\n\nPROBLEM: Statement: <MASK>, ಮೂರರಿಂದ ಆರು ವರ್ಷ ವಯಸ್ಸಿನ ನಡುವಿನ ಮಕ್ಕಳ ಶಾಲಾಶಿಕ್ಷಣಕ್ಕೆ ನಿಡೋ ಎಂದು ಸೂಚಿಸಲಾಗುತ್ತದೆ. ಇದರ ನಂತರ ನಾಲ್ಕು ವರ್ಷದ ಪ್ರಾಥಮಿಕ ಶಿಕ್ಷಣ ತರಗತಿಗಳು ನಡೆಯುತ್ತವೆ. ಕೆಲವು ಪೋಷಕರು ತಮ್ಮ ಮಕ್ಕಳನ್ನು ಆರನೇ ವರ್ಷದಲ್ಲಿ ಪ್ರಾಥಮಿಕ ಶಾಲೆಗೆ ದಾಖಲು ಮಾಡುತ್ತಾರೆ. ಇಸವಿ ೧೯೦೨ರಲ್ಲಿ, ಶಿಕ್ಷಕಿ ಎಲ್ವಿರ ಗಾರ್ಸಿಯ ಹಾಗು ಗಾರ್ಸಿಯಾ ಎಂಬ ಸಂಸ್ಥೆಯ ಸಹ ಸ್ಥಾಪಕಿ, ಎರಡರಿಂದ ಎಂಟು ವರ್ಷದ ಮಕ್ಕಳಿಗಾಗಿ ಮೊದಲ ಬಾರಿಗೆ ಶಿಶುವಿಹಾರ ಪ್ರಾರಂಭಿಸುತ್ತಾರೆ, ಜೊತೆಗೆ ಮಹಿಳೆಯರಿಗೆ ವಿಶೇಷ ಶಿಕ್ಷಣ-ತರಬೇತಿಗಾಗಿ ಒಂದು ಉಪವಿಭಾಗವನ್ನು ಆಕೆ ಈ ಸಂದರ್ಭದಲ್ಲಿ ಸೃಷ್ಟಿಸಿದರು. ಆಕೆಯ ಅಧ್ಯಯನಗಳು ಹಾಗು ಮಕ್ಕಳ ಬಗೆಗಿನ ಕಾಳಜಿಯನ್ನು ಸಮಾಲೋಚನೆಗಳು ಹಾಗು ಹಲವಾರು ಆಧಾರಗಳ ಮೂಲಕ ಪ್ರಸಾರ ಮಾಡುವ ಅವಕಾಶ ದೊರೆಯಿತು, ಬಾಲ್ಯದಲ್ಲೇ ಮಕ್ಕಳ ರಕ್ಷಣೆಯ ಪ್ರಾಮುಖ್ಯತೆ ಹಾಗು ನ್ಯಾಯ ಹಾಗು ತಿಳಿವಳಿಕೆಯಿಂದ ವ್ಯಕ್ತಿತ್ವವನ್ನು ರೂಪಿಸಲು ಸ್ಪಂದಿಸಬೇಕು, ಜೊತೆಗೆ ಫ್ರೋಬೇಲ್ ವಿಧಾನಗಳ ಬಳಕೆ ಹಾಗು ಮಾಂಟೆಸ್ಸರಿ ಪದ್ಧತಿ ಹಾಗು ಈ ಶೈಕ್ಷಣಿಕ ಕಾರ್ಯಗಾರದಲ್ಲಿ ಪೋಷಕರ ಪಾಲ್ಗೊಳ್ಳುವಿಕೆ.\n\n Option A: ಪೆರುವಿನಲ್ಲಿ\n\n Option B: ಇಸ್ರೇಲ್\n\n Option C: ಕೆನಡಾದ\n\n Option D: ವೆನಿಜುವೆಲ\n\nSOLUTION:",
"role": "user"
},
{
"content": "ಪೆರುವಿನಲ್ಲಿ\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_84373
|
[
{
"content": "In this task, you are given triplets. Each triplet is in the form of [subject, predicate, object]. Your task is to generate proper sentence that utilizes these triples. The objective is to construct a sentence that (a) captures the facts specified in the triples and (b) is a well-formed sentence easily understandable by a human. All triple values need not be used directly in the sentence as long as the facts are adequately captured.\n\nEx Input:\n[['Lockheed SR-71 Blackbird', 'SPEED_(MPH)', '2,194'], ['Lockheed SR-71 Blackbird', 'PILOT', 'Eldon W. Joersz']]\n\nEx Output:\nEldon W. Joersz piloted the Lockheed SR-71 Blackbird as it travelled 2,194 mph.\n\n\nEx Input:\n[['The Golden Curry', 'food', 'Indian'], ['The Golden Curry', 'customer rating', '1 out of 5'], ['The Golden Curry', 'area', 'riverside'], ['The Golden Curry', 'familyFriendly', 'yes'], ['The Golden Curry', 'near', 'Café Rouge']]\n\nEx Output:\nThe Golden Curry is kids friendly and serves Indian food in riverside. It is located near Café Rouge and has customer rating of 1 out of 5.\n\n\nEx Input:\n[['[TABLECONTEXT]', 'PLAYER', 'Mitch Trubisky'], ['[TABLECONTEXT]', '[TITLE]', 'Mr. Football Award (Ohio)'], ['Mitch Trubisky', 'COLLEGE', 'North Carolina'], ['Mitch Trubisky', 'YEAR', '2012']]\n\nEx Output:\n",
"role": "user"
},
{
"content": "Mitch Trubisky, from North Carolina, won the Mr. Football Award in Ohio in 2012.\n\n\n",
"role": "assistant"
}
] |
cot
|
cot_62869
|
[
{
"content": "Q: If \"A line of people walking down the street.\" does that mean that \"On the street are a column of people headed through town.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: A line of people and a column of people have similar meaning.\nThe answer is yes.\nQUESTION: Can we conclude from \"A man in jeans with red shoes bicycles down a street past a brick building.\" that \"A man driving a car.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\n\nLet's solve it slowly: A man driving a car cannot bicycle at the same time.\nThe answer is no.\n[QUESTION] Given the sentence \"The coach talks it over with his quarterback during a timeout.\" is it true that \"A man types on his keyboard.\"?\nA coach cannot cannot talk with quarterback and type on his keyboard at the same time.\nThe answer is no.\nQ: Test for natural language inference.\nPremise: \"A person is reaching out of a window in a high rise to pull on a rope pulley.\"\nHypothesis: \"A person is nude while holding a rope.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: A person reaching out of a window to pull on a rope is not necessarily nude.\nThe answer is it is not possible to tell.\nQUESTION: Premise: \"A group of men and boys loading and tying down items at the rear and on top of a bus.\"\nHypothesis: \"There is a group of people tying down things onto the bus.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: A group of men refers to there is a group of people.\nThe answer is yes.\nQUESTION: Can we conclude from \"Father and son swimming.\" that \"The two people are having fun.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\n\nLet's solve it slowly:",
"role": "user"
},
{
"content": "Father and son swimming does not infer two people have fun.\nThe answer is it is not possible to tell.",
"role": "assistant"
}
] |
cot
|
cot_96796
|
[
{
"content": "QUESTION: Given the sentence \"A crowd is staring at a screen that is showing a colorful image.\" can we conclude that \"The crowd is eating dinner.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: People in a crowd do not usually stare at a screen while simultaneously eat dinner.\nThe answer is no.\n[QUESTION] Premise: \"Four guys in a car with one in the middle seat turned backwards looking at the camera.\"\nHypothesis: \"Four guys are sleep in their home.\"\nDo we know that the hypothesis entailed by the premise?\nFour guys are either in a car or sleeping in their home.\nThe answer is no.\nQ: Test for natural language inference.\nPremise: \"Children play in the dark water fountain near the white triumphal arch while adults sit on the steps.\"\nHypothesis: \"Children are playing cops and robbers by a water fountain.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: Children playing does not mean they are playing cops and robbers.\nThe answer is it is not possible to tell.\nQUESTION: Given the sentence \"Two women sit in front of a teal building with a red iron roof.\" is it true that \"Two women sit in front of a building with a red roof.\"?\n\nLet's solve it slowly: A building can be teal in color and the red roof can be made of iron.\nThe answer is yes.\n[QUESTION] If \"A young boy who is wearing a helmet looks at a bicycle.\" does that mean that \"A young boy is riding a skateboard.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nThe boy is either riding a skateboard or looking at a bicycle.\nThe answer is no.\nQ: Premise: \"A cook prepares food in a restaurant kitchen.\"\nBased on this premise, can we conclude that the hypothesis \"A cook makes saag paneer.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA:",
"role": "user"
},
{
"content": "If you on'y prepares food then you're not making saag paneer.\nThe answer is it is not possible to tell.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_89536
|
[
{
"content": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nIn this task, you're shown a three-part story, with a beginning, middle, and ending. Your job is to slightly modify the middle part, so that the whole story becomes unlikely, improbable, or inconsistent. Generated sentences must minimally alter the given middle, with at most 4 new words added/existing words removed. Your sentence should be grammatically and syntactically correct. Also stick to the context of the given story. For example, if the story talks about \"doctors\", you can talk about \"health\" or \"diagnosis\", but don't mention \"aliens\". Avoid introducing any extra/irrelevant information, and use names instead of pronouns (e.g. he / she) wherever possible. Avoid simply negating the original middle, for example: \"She likes cakes.\" is changed to \"She doesn't like cakes.\"\n\nBeginning: Lauren finished her late night shift at the bar feeling tired. Middle: Lauren took a long hot bath when she got home. Ending: Lauren's husband was glad to see her feeling refreshed.\nSolution: Lauren's husband took a long hot bath when he got home.\nWhy? If a person takes a bath, another person's tiredness is not reduced.\n\nNew input: Beginning: Two young girls had a dream after high school to take a road trip. Middle: The two young girls made the dream a reality. Ending: Both girls hope this is something they will continue in the future.\nSolution:",
"role": "user"
},
{
"content": "The two young boys made the dream a reality.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_91237
|
[
{
"content": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nIn this task, you're shown a three-part story, with a beginning, middle, and ending. Your job is to slightly modify the middle part, so that the whole story becomes unlikely, improbable, or inconsistent. Generated sentences must minimally alter the given middle, with at most 4 new words added/existing words removed. Your sentence should be grammatically and syntactically correct. Also stick to the context of the given story. For example, if the story talks about \"doctors\", you can talk about \"health\" or \"diagnosis\", but don't mention \"aliens\". Avoid introducing any extra/irrelevant information, and use names instead of pronouns (e.g. he / she) wherever possible. Avoid simply negating the original middle, for example: \"She likes cakes.\" is changed to \"She doesn't like cakes.\"\n\nBeginning: Lauren finished her late night shift at the bar feeling tired. Middle: Lauren took a long hot bath when she got home. Ending: Lauren's husband was glad to see her feeling refreshed.\nSolution: Lauren's husband took a long hot bath when he got home.\nWhy? If a person takes a bath, another person's tiredness is not reduced.\n\nNew input: Beginning: We live in a basement unit in a condo. Middle: A mouse got into the cereal box. Ending: Luckily we never saw the rat.\nSolution:",
"role": "user"
},
{
"content": "A mouse got into the anti-rye box.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_81327
|
[
{
"content": "You will be given a definition of a task first, then some input of the task.\nIn this task, you're given an article and an answer. Your task is to generate the fill-in-the-blank question for this answer based on the given article. The blanks are always at the end of the question, and can be filled with more than one word or phrase.\n\nArticle: Some years ago, on a hot summer day in south Florida, a little boy decided to go for a swim in the cold swimming hole behind his house. In a hurry to dive into the cool water, he did not realize an alligator was swimming towards the shore. His mother in the house, looking out of the window, saw the two as they got closer and closer together. In fear, she ran towards the water, yelling to the son as loudly as she could. It was too late. The alligator reached him. From the dock, the mother grabbed her little boy by the arms just as the alligator got his legs. That began an incredible tug of war between the two. The alligator was much stronger than the mother, but the mother would not let go. A farmer happened to drive by, heard her screams, ran from his truck, and shot the alligator. Amazingly, after weeks and weeks in the hospital, the little boy survived. His leg were extremely scarred by the animal's attack, and on his arms were scratches from mothers' fingernails where she had tried to hang on to the son she loved. The newspaper reporter who interviewed the boy asked if he would show him his scars. The boy lifted his pant legs . And then, he proudly said to the reporter: \"But look at my arms. I have great scars on my arms, too. I have them because my mom would not let go.\" You and I can identify with that little boy. We have scars, too. No, not from alligator, or anything quite so dramatic . But the scars of a painful past. Some of those scares are ugly and have caused us deep regret. But some wounds, my friend, are because someone has refused to let go. In your struggle, maybe someone has been there holding on to you. \n Answer: got ready to fight the crocodile\nOutput:",
"role": "user"
},
{
"content": "Upon seeing the alligator getting close to her boy, the mother _ .",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_54715
|
[
{
"content": "input: Please answer the following: Lee flew back home but needed to make sure their parents would be around to visit. Given that the answer to a question is \"call their parents\", what is the question?\n++++++++++\noutput: What does Lee need to do before this?\n\n\nPlease answer this: Kai wished they could have some pets. Kai coveted their neighbor's pets. Given that the answer to a question is \"jealous\", what is the question?\n++++++++\nAnswer: How would Kai feel afterwards?\n\n\nProblem: Jan just got out of the shower. Jan got their towel to put around them. Given that the answer to a question is \"relaxed\", what is the question?\n\nA: How would you describe Jan?\n\n\nProblem: Given the question: Sasha told their friends they could stay at their house that night. Given that the answer to a question is \"ask permission\", what is the question?\n++++++++++++++++++++++++++++++++\nThe answer is:\nWhat does Sasha need to do before this?\n\n\ninput question: Alex played the game all the time, but they could never beat the final level. Given that the answer to a question is \"embarrassed\", what is the question????\noutput answer: How would Alex feel afterwards?\n\n\ninput question: Riley walked to work in the morning, because their car was in the shop. Given that the answer to a question is \"find out when their car will be done\", what is the question????\noutput answer:",
"role": "user"
},
{
"content": "What will Riley want to do next?",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_13275
|
[
{
"content": "Question: Sentence A: right and i mean you can you can buy an extra screen but but it's somehow because the screen comes with it it it always looks awkward to have the two screens\n\nSentence B: you can get another screen if you want one, but it looks strange to have two of them\n\nIf sentence A is true, how about sentence B?\nOPTIONS:\n- yes\n- it is not possible to tell\n- no\n\nAnswer: yes\n\n\nQuestion: Sure, there are some from other courts elsewhere, but they are few and far between, and Starr really wouldn't be able to cite them properly in a brief in the District of Columbia.\nStarr would be able to cite all things from the other courts in a brief in the District of Columbia. \nOPTIONS:\n- yes\n- it is not possible to tell\n- no\n\nAnswer: no\n\n\nProblem: Here is a premise:\nBeside David and Goliath, Daniel in the lions' den, and the building of Noah's ark, one curious sculpture shows Saint Eugenia, tonsured and disguised as a monk, opening her robe to convince a skeptical friar that she's a woman.\n\nHere is a hypothesis:\nSaint Eugenia is pictured in many different religions.\n\nHere are the options: OPTIONS:\n- yes\n- it is not possible to tell\n- no\n\nAnswer: it is not possible to tell\n\n\nSentence 1: Half an hour in the morning and late afternoon creates the groundwork for a good tan.\n\nSentence 2: Tanning is common among beachgoers.\nOPTIONS:\n- yes\n- it is not possible to tell\n- no\nIs this second sentence entailed by the first?\n\nAnswer: it is not possible to tell\n\n\nQuestion:\nAlthough the Disaster Recovery Center will open Friday, it is extremely important for individuals and businesses to call the FEMA disaster number to begin the application process.\n\nDoes it follow that \"On Friday, the disaster recovery center will be closed and individuals can call.\"?\nOPTIONS:\n- yes\n- it is not possible to tell\n- no\nAnswer:\nno\n\n\nQuestion:\nBased on the premise \"On either side lie the ruins of sepulchres of 20 generations of patrician families.\", can we conclude that \"On either side lie the ruins of medieval castles.\"? OPTIONS:\n- yes\n- it is not possible to tell\n- no\n****\nAnswer:\n",
"role": "user"
},
{
"content": "no",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_84096
|
[
{
"content": "In this task, you're given a statement and three sentences as choices. Your job is to determine the neutral choice based on your inference from the statement and your commonsense knowledge. The neutral choice is a sentence that neither agrees nor disagrees with the statement. Indicate your answer as '1', '2', or '3', corresponding to the choice number of the selected sentence. If sentence X agrees with sentence Y, one's correctness follows from the other one. If sentence X disagrees with sentence Y, they can not be correct at the same time.\n\nExample Input: Statement: A short walk from the Piazza della Vittoria takes you to the island-famous Villa San Michele, home of Swedish doctor-writer (and great lover of Capri) Axel Munthe (d. Choices: 1. The Villa San Michele is situated on its own island. 2. The Villa San Michele is nearby the Piazza della Vittoria. 3. Axel Munthe was a Swiss doctor.\nExample Output: 1\n\nExample Input: Statement: The dry-cleaning bills were ridiculous. Choices: 1. I couldn't believe how cheap the dry cleaning was. 2. It cost $200 to have one article dry cleaned. 3. The dry-cleaning was expensive. \nExample Output: 2\n\nExample Input: Statement: Station XII (Jesus's death): To the left of the Franciscan chapel is a Greek Orthodox altar, profusely decorated with hanging oil lamps. Choices: 1. There are no lamps hanging anymore. 2. There are oil lamps hanging on the tall stone walls. 3. There are oil lamps hanging on the altar.\nExample Output:",
"role": "user"
},
{
"content": "2\n\n",
"role": "assistant"
}
] |
cot
|
cot_68516
|
[
{
"content": "Q: Given the sentence \"A child wearing a gray hat and black jacket while sleeping on a red coat.\" can we conclude that \"The child is lost.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: A sleeping child does not imply that the child is lost.\nThe answer is it is not possible to tell.\n\nQ: Given the sentence \"There are lots of beautiful pink and white flowers and two asian girls playing in them.\" is it true that \"Two boys are tearing the flowers out of the ground.\"?\nA: Two Asian girls are not the same thing as two boys.\nThe answer is no.\n\nQ: Premise: \"Several girls on a raft floating in rough waters.\"\nHypothesis: \"The are more than one girls on the boat.\"\nDo we know that the hypothesis entailed by the premise?\nA: Several implies more than one girl and a raft is a form of boat.\nThe answer is yes.\n\nQ: Premise: \"A black dog jumping a wire fence with a dead bird in his mouth.\"\nBased on this premise, can we conclude that the hypothesis \"The dog jumped the fence.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA:",
"role": "user"
},
{
"content": "One has to be jumping a fence to jumped the fense.\nThe answer is yes.",
"role": "assistant"
}
] |
cot
|
cot_61674
|
[
{
"content": "Explanation for the following question's answer: A rubik's cube needs to be physically restored.\nQuestion: Which of the following sentences is nonsensical?\nOptions:\n- Sentence A: \"He restored the Rubik's Cube with his eyes\"\n- Sentence B: \"He restored the Rubik's Cube with his hand.\"\n\nAnswer: Sentence A\nChain-of-thought: People can't eat on the ceiling because gravity would pull them down.\n--\nQuestion: Of the below sentences, which one does *not* make sense?\nOptions:\n- Sentence A: \"my parents eat lunch at table\"\n- Sentence B: \"my parents eat lunch on the ceiling\"\n\nAnswer: Sentence B\nChain-of-thought: Enemies are not happy when you are happy.\n\nQuestion: Of the below sentences, which one does *not* make sense?\nOptions:\n- Sentence A: \"The enemy shares your joys and sorrows\"\n- Sentence B: \"The friend shares your joys and sorrows\"\n\nAnswer: Sentence A\nExplanation for the following question's answer: The person who wins the bet is the person who gives the orders.\nQuestion: Pick which sentence is not logical.\nOptions:\n- Sentence A: \"If my brother loses the bet, I will order him to do all my chores.\"\n- Sentence B: \"If my brother wins the bet, I will order him to do all my chores.\"\n\nAnswer: Sentence B\nChain-of-thought: People do not have pet days because people do not act like pets for periods of their life.\n--\nQuestion: One of the following sentences is nonsensical. Which one is it?\nOptions:\n- Sentence A: \"the pictures remind me of my pet days\"\n- Sentence B: \"the pictures remind me of my school days\"\n\nAnswer: Sentence A\nChain-of-thought: Dinosaurs and Mary did not live in an era.\n\n",
"role": "user"
},
{
"content": "Question: Choose the sentence that goes against common sense.\nOptions:\n- Sentence A: \"Mary is walking her dogs.\"\n- Sentence B: \"Mary is walking her dinosaurs.\"\n\nAnswer: Sentence B",
"role": "assistant"
}
] |
cot
|
cot_79657
|
[
{
"content": "Q: Given the sentence \"A man in a white shirt with hot pads on is holding a tray with a variety of breads with a wooden fence behind him.\" is it true that \"The man is taking his driver's test.\"?\nA: Holding a tray cannot be done while taking a driver's test.\nThe answer is no.\nQUESTION: If \"A group of men in oriental attire are celebrating.\" does that mean that \"They are friends with each other.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: A group of men in oriental attire does not imply they are friends.\nThe answer is it is not possible to tell.\n[QUESTION] Given the sentence \"A little girl is smiling whilst wearing a fake nose and glasses.\" can we conclude that \"The glasses are round.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA girl wearing a fake nose and glasses doesn't imply glasses are round.\nThe answer is it is not possible to tell.\nQ: Test for natural language inference.\nPremise: \"A woman sitting against a brick wall inside a building.\"\nHypothesis: \"A woman is reading a magazine inside a building.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: We cannot infer her actions inside the building and assume she is reading a magazine.\nThe answer is it is not possible to tell.\nQUESTION: If \"In the beach a woman is balancing a basket of shells on her head.\" does that mean that \"A lady has a basket on her head because it makes people laugh.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: People don't balance baskets on their heads just because it makes people laugh.\nThe answer is it is not possible to tell.\nQUESTION: Premise: \"An artist is creating his metal works or art outside using a fire and hammer.\"\nBased on this premise, can we conclude that the hypothesis \"An artist using paint and fire on a canvas.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly:",
"role": "user"
},
{
"content": "The artist can't be creating metal works and using paint on a canvas at the same time.\nThe answer is no.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_84970
|
[
{
"content": "Given the task definition, example input & output, solve the new input case.\nIn this task, you are given two lists A,B. Find the longest common subsequence in the lists A and B.\nExample: [5797, 8817, '8297', 'b', 'U', 'b'], [5843, 8809, '8297', 'b', 'W', 'C']\nOutput: 8297, b\nHere, '8297, b' is the longest common subsequence in both the input lists [5797, 8817, '8297', 'b', 'U', 'b'] and [5843, 8809, '8297', 'b', 'W', 'C'].\n\nNew input case for you: ['Y', 3139, 'C', 'G', 'y', 1155, 'b', 'i', 'Q', 'p', '2431', 'O', 'n', '6495', '2389', 'c', '925', '2407', '3985', '7945', 'n', 'n', 3073, 'm', 'y', 'V', 'p', 9923, 'q', 6203, 'W'], ['b', 'l', 19, 8607, 'Q', 'p', '2431', 'O', 'n', '6495', '2389', 'c', '925', '2407', '3985', '7945', 'n', 'M', 'f', 6469, 4579, 911, 'f', 'e']\nOutput:",
"role": "user"
},
{
"content": "Q, p, 2431, O, n, 6495, 2389, c, 925, 2407, 3985, 7945, n",
"role": "assistant"
}
] |
cot
|
cot_60091
|
[
{
"content": "QUESTION: Can we conclude from \"Three people are making the cashier busy inside the grocery store.\" that \"Three people are buying all the party supplies for the party.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\n\nLet's solve it slowly: People can buy things without it being party supplies for a party.\nThe answer is it is not possible to tell.\n[QUESTION] Can we conclude from \"Two people dressed in athletic clothing walk down the street.\" that \"While the taller of the two is holding a basketball.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nTwo guys are walking to the basketball court to play a game of basketball.\nThe answer is yes.\nQ: Premise: \"The black dog is wearing a red collar and is jumping into the water after a frisbee.\"\nHypothesis: \"An animal in water.\"\nDo we know that the hypothesis entailed by the premise?\nA: Black dog jumping into the water after a Frisbee shows an animal in water.\nThe answer is yes.\nQUESTION: Given the sentence \"A man talking to a group of people.\" is it true that \"The man is talking with people.\"?\n\nLet's solve it slowly: Talking with people is a way to rephrase taking to a group of people.\nThe answer is yes.\n[QUESTION] Premise: \"People watch as a bunch of boys stand around and perhaps hold still a large pole.\"\nBased on this premise, can we conclude that the hypothesis \"The boys are playing tetherball.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA bunch of boys who hold still a large pole are not necessarily playing tetherball.\nThe answer is it is not possible to tell.\nQ: Premise: \"A person is running up a field with a football.\"\nHypothesis: \"Playing chess on the grass.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA:",
"role": "user"
},
{
"content": "A running up a field with a football cannot be playing chess the same time.\nThe answer is no.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_91598
|
[
{
"content": "You will be given a definition of a task first, then an example. Follow the example to solve a new instance of the task.\nIn this task, you're given the title of a five-sentence story, the first four sentences, and two options for the fifth sentence as a and b. Your job is to pick the sentence option that does not connect with the rest of the story, indicating your choice as 'a' or 'b'. If both sentences are plausible, pick the one that makes less sense.\n\nTitle: Marcus Buys Khakis. Sentence 1: Marcus needed clothing for a business casual event. Sentence 2: All of his clothes were either too formal or too casual. Sentence 3: He decided to buy a pair of khakis. Sentence 4: The pair he bought fit him perfectly. Choices: a. Marcus was happy to have the right clothes for the event. b. He left in a huff for having his ideas mocked.\nSolution: b\nWhy? Marcus is buying clothes for a business event and not presenting an idea.\n\nNew input: Title: Struggles with openings.. Sentence 1: I found myself locked in my room without a way to open my door. Sentence 2: In a state of disarray, I began to punch and kick the door feverishly. Sentence 3: Finding this to be no help, I launched into the frame. Sentence 4: As the wood began to split in half, I realized what I had done. Choices: a. The puppy made her really happy again. b. I switched the doorknobs in a rage and forgot to set it to unlock!\nSolution:",
"role": "user"
},
{
"content": "a",
"role": "assistant"
}
] |
cot
|
cot_73480
|
[
{
"content": "[QUESTION] Given the sentence \"Four men are leaping into the air while the fifth man is standing on the ground outside of a house.\" is it true that \"All the men are leaping into the air.\"?\nAll the men cannot be simultaneously leaping in the air if the fifth man remains standing.\nThe answer is no.\nQ: Test for natural language inference.\nPremise: \"A girl in a purple dress is throwing a tantrum.\"\nHypothesis: \"The girl is playing soccer.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: The girl can't actively be playing soccer and throwing a tantrum at the same time.\nThe answer is no.\nQUESTION: Can we conclude from \"A balloon vendor stands in the street while motorcycles drive by.\" that \"A vendor is in the street.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\n\nLet's solve it slowly: The vendor is in the street because he/she stands in the street.\nThe answer is yes.\n[QUESTION] Given the sentence \"The child is playing hide and seek in the hay.\" is it true that \"The girl is playing hide and seek in her closet.\"?\nOne is in the hay and one is in the closet. Hay is usually outside.\nThe answer is no.\nQ: Test for natural language inference.\nPremise: \"A woman with black hair wearing a sleeveless dress stands next to a car.\"\nHypothesis: \"An actress getting out of a limo on her way to an award show.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: A woman wearing a sleeveless dress who stands next to a car does not mean the woman is an actress or the car is a limo or that she is on her way to an awards show.\nThe answer is it is not possible to tell.\n[QUESTION] If \"A man jumps gin the air while riding an atv.\" does that mean that \"The man is reckless.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n",
"role": "user"
},
{
"content": "A man jumping gin the air while riding an ATV is not always reckless.\nThe answer is it is not possible to tell.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_91031
|
[
{
"content": "In this task, you are given inputs i and A, where i is an integer and A is a list. You need to list all the elements of A after the first i elements. i will always have a value less than the length of A.\n\n[Q]: 5, ['171', 'Y', 'k', 'e', 'A', 't', 'O', 'R', 'c', '2401', 'i', '8629', '7015']\n[A]: t, O, R, c, 2401, i, 8629, 7015\n\n\n[Q]: 8, ['3361', 'x', 'q', '9571', '1553', '6021', 'x', '8065', 'Q', '9335', 'Q', 'i', 'M', '7665', '2081', 'B']\n[A]: Q, 9335, Q, i, M, 7665, 2081, B\n\n\n[Q]: 3, ['D', '9665', 'v', 'Q', '3379', '6647', 'q', '13', 'c', '3547', 'm', 'C']\n[A]:",
"role": "user"
},
{
"content": "Q, 3379, 6647, q, 13, c, 3547, m, C\n\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_82514
|
[
{
"content": "Teacher: In this task, you are given a short story consisting of exactly 5 sentences where the second sentence is missing. You are given two options and you need to select the one that best connects the first sentence with the rest of the story. Indicate your answer by 'Option 1' if the first option is correct, otherwise 'Option 2'. The incorrect option will change the subsequent storyline, so that at least one of the three subsequent sentences is no longer consistent with the story.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nSentence 1: The cashier was counting the dollar bills at her desk. \n Sentence 3: Everyone panicked and started to scream. \n Sentence 4: The men threatened the people to remain quiet. \n Sentence 5: The cashier handed them the cash so they would go away. \n Option 1: Two men rushed into the store and held their guns up. \n Option 2: Two dogs rushed into the store.\nSolution: Option 1\nReason: Option 1 forms a consistent story with the given four sentences. In constrast, Option 2 is incorrect as the entty 'two dogs' is not consistent with 'men' mentioned in Sentence 4.\n\nNow, solve this instance: Sentence 1: Uncharacteristically, Malik ran toward the brouhaha. \n Sentence 3: A path cleared in the middle of the crowd cleared for him \n Sentence 4: His mother was finally revealed, sweating and bewildered \n Sentence 5: He walked slowly toward her, his hand outstretched to make contact \n Option 1: He could hear his mother laughing as he approached. \n Option 2: He could hear his mother shouting his name as he approached.\nStudent:",
"role": "user"
},
{
"content": "Option 2",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_88482
|
[
{
"content": "In this task, you are given an input list. A list contains several comma-separated items written within brackets. You need to return the count of all the numerical elements in the given list. Return 0 if no numerical element in the list.\n--------\nQuestion: ['x', '8799', 'y', '2165', 'K', '6381', '85', 'R', 'D', 'Y', 'i', 'l', 'n', '1707', 'G', 'q', '5321', 'z', 'O', '2877', 'X', '3117', 'N', '9489', 'W', '1475', 'o', '4625', '3853', 'o', 'Y', '6987', 'C', 'c', 'm']\n\nAnswer: 13\n\n\nQuestion: ['6465', 'R', 'z', '1197', 'a', 'X', '3337', '8609', '8401', 'i', '4915', '2381', '861']\n\nAnswer: 8\n\n\nQuestion: ['4409', '4637', '553', '1485', '6671', 'I', 'I', '5453', '7227', 'm', 'P', '391', 'A', 'q', 'o', '9347', 'j', 's', 'r', '7939', '4869', 'b', 'J', 'a', 't', '6925', '4303', 'H', 'S', 'N']\n\nAnswer:",
"role": "user"
},
{
"content": "13\n\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_13456
|
[
{
"content": "Sentence 1: It consists of two spans, straddling the Ile de la City, and was initially populated with street-singers, charlatans, prosetutes, pickpockets, and above all bouquinistes selling old books and pamphlets out of boxes.\n\nSentence 2: Bouquinistes used boxes to sell old books and pamphlets.\nOPTIONS:\n- yes\n- it is not possible to tell\n- no\nIs this second sentence entailed by the first?\n\nAnswer: yes\n\n\nQuestion:\nah i jig when they jog\n\nDoes it follow that \"I jig when they run.\"?\nOPTIONS:\n- yes\n- it is not possible to tell\n- no\nAnswer:\nyes\n\n\nQ: If yeah well when i bought my car it was right out of college and uh you know i always been looking for something sporty and i ended up getting you know basically something that i could you know afford, can we say that \"I always wanted a car that was sporty. \"?\nOPTIONS:\n- yes\n- it is not possible to tell\n- no\n\nA: yes\n\n\nPremise:\n\"sexual crimes unless there's a true change of character and that's where we just have to to trust the authorities and they're not going to excuse people if it was was run like that i don't there would probably be very few exceptions to that and if it was done quickly and done swiftly and but it's not because the judicial system has rejected they've rejected the answer to all these problems they have pretty much\"\nHypothesis: People that commit sexual crimes commonly change their character.\nOPTIONS:\n- yes\n- it is not possible to tell\n- no\n\nno\n\n\ninput question: I suppose secret service work makes you like that! In the pause that ensued, Mr. Carter took from his pocket a small shabby brown book. If this premise is true, does that tell us:\"Mr. Carter was not in possession of any books at the time, brown or no. \"?\n\nOPTIONS:\n- yes\n- it is not possible to tell\n- no\n\noutput answer: no\n\n\nQ: If The only US president to resign, Nixon is recognized for his contributions to foreign affairs during the Cold War years., can we say that \"Nixon's policies were controversial during a volatile time.\"?\nOPTIONS:\n- yes\n- it is not possible to tell\n- no\n\nA:",
"role": "user"
},
{
"content": "it is not possible to tell",
"role": "assistant"
}
] |
cot
|
cot_59615
|
[
{
"content": "Q: Premise: \"Two people jump up and down on a cliff overlooking a valley.\"\nBased on this premise, can we conclude that the hypothesis \"Two people on a cliff are excited to have made it to the top to see the beautiful valley.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: Just because they jump up and down does not mean they are excited.\nThe answer is it is not possible to tell.\nQUESTION: Given the sentence \"A woman wearing jeans and brown flip-flops holding two blond-hair toddler girls wearing pink shorts and shoes.\" is it true that \"The woman is responsible for the two small children.\"?\n\nLet's solve it slowly: There is a a woman that has two toddler girls she is looking after.\nThe answer is yes.\n[QUESTION] Can we conclude from \"A number of young people are having fun in a pool trying out their log-rolling skills.\" that \"The people are sitting beside the pool.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA number of young people can not having fun in a pool and be sitting beside the pool simultaneously.\nThe answer is no.\nQ: Can we conclude from \"A young boy in a black sweatshirt and red vest plays on a red jungle gym.\" that \"A boy is playing with his friends on the jungle gym.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: To play on a jungle gym does not imply it is with friends.\nThe answer is it is not possible to tell.\nQUESTION: Given the sentence \"A young boy sits backwards while riding a donkey in an open hilly field.\" can we conclude that \"The boy is riding a donkey in the subway.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: A boy riding a donkey in the subway can not be in an open hilly field.\nThe answer is no.\nQUESTION: If \"Girls in white shirts and blue skirts shoot arrows from bows.\" does that mean that \"A group of females are taking a nap.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly:",
"role": "user"
},
{
"content": "Girls cannot be taking nap and shoot arrows at same time.\nThe answer is no.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_86362
|
[
{
"content": "In this task, you're shown a three-part story, with a beginning, middle, and ending. Your job is to slightly modify the middle part, so that the whole story becomes unlikely, improbable, or inconsistent. Generated sentences must minimally alter the given middle, with at most 4 new words added/existing words removed. Your sentence should be grammatically and syntactically correct. Also stick to the context of the given story. For example, if the story talks about \"doctors\", you can talk about \"health\" or \"diagnosis\", but don't mention \"aliens\". Avoid introducing any extra/irrelevant information, and use names instead of pronouns (e.g. he / she) wherever possible. Avoid simply negating the original middle, for example: \"She likes cakes.\" is changed to \"She doesn't like cakes.\"\n\nEx Input:\nBeginning: Lisa was planning on eating leftovers for lunch. Middle: She tasted the food and it was gross. Ending: She reluctantly threw the food out.\n\nEx Output:\nShe tasted the food and it was delicious.\n\n\nEx Input:\nBeginning: I got a vase for Christmas last year. Middle: I shipped it to my new home with lots of bubble wrap. Ending: It had arrived safely!\n\nEx Output:\nI shipped it to my new house with no filler material.\n\n\nEx Input:\nBeginning: Ben decided to help his community. Middle: Ben organized a food drive and collected hundreds of cans. Ending: Ben felt so good about helping out!\n\nEx Output:\n",
"role": "user"
},
{
"content": "Ben anti-methodized a food drive and collected hundreds of cans.\n\n\n",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_86805
|
[
{
"content": "In this task, you are given a short story consisting of exactly 5 sentences where the second sentence is missing. You are given a candidate for the second sentence and you need to identify if the given sentence connects the first sentence with the rest of the story. Indicate your answer by \"Yes\" if it connects, otherwise \"No\". Do not generate anything else apart from \"Yes\" or \"No\". The given sentence is incorrect if it changes the subsequent storyline, so that at least one of the three subsequent sentences form a consistent story.\nOne example is below.\nQ: Sentence 1: The cashier was counting the dollar bills at her desk. \n Sentence 3: Everyone panicked and started to scream. \n Sentence 4: The men threatened the people to remain quiet. \n Sentence 5: The cashier handed them the cash so they would go away. \n Given Sentence 2: Two men rushed into the store and held their guns up.\nA: Yes\nRationale: People panic when somebody holds their guns up. Sentence 2 correctly connects Sentence 1 with rest of the story. So, the answer is 'Yes'.\nQ: Sentence 1: Sue loves to browse the internet while she drinks her morning coffee. \n Sentence 3: Frustrated, she calls the internet provider to get it fixed \n Sentence 4: A technician is sent to her house right away \n Sentence 5: The technician arrives by lunchtime and fixes the internet \n Given Sentence 2: He suggested they walk around the town's fountain.\nA:",
"role": "user"
},
{
"content": "No",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_89012
|
[
{
"content": "In this task, you're shown a three-part story, with a beginning, middle, and ending. Your job is to slightly modify the middle part, so that the whole story becomes unlikely, improbable, or inconsistent. Generated sentences must minimally alter the given middle, with at most 4 new words added/existing words removed. Your sentence should be grammatically and syntactically correct. Also stick to the context of the given story. For example, if the story talks about \"doctors\", you can talk about \"health\" or \"diagnosis\", but don't mention \"aliens\". Avoid introducing any extra/irrelevant information, and use names instead of pronouns (e.g. he / she) wherever possible. Avoid simply negating the original middle, for example: \"She likes cakes.\" is changed to \"She doesn't like cakes.\"\nOne example: Beginning: Lauren finished her late night shift at the bar feeling tired. Middle: Lauren took a long hot bath when she got home. Ending: Lauren's husband was glad to see her feeling refreshed.\nSolution is here: Lauren's husband took a long hot bath when he got home.\nExplanation: If a person takes a bath, another person's tiredness is not reduced.\n\nNow, solve this: Beginning: Jack was a great tap dancer. Middle: Jack took more tap lessons. Ending: Jack danced his heart out and won the talent show.\nSolution:",
"role": "user"
},
{
"content": "Jack started taking wrestling lessons.",
"role": "assistant"
}
] |
cot
|
cot_73157
|
[
{
"content": "Q: If \"A red dog jumps to catch a tennis ball in the dry tall grass.\" does that mean that \"Dog playing in the park.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: The dog jumping in the grass does not imply it is playing in the park.\nThe answer is it is not possible to tell.\nQUESTION: Given the sentence \"Two men are walking in a street of stone on a nice day.\" can we conclude that \"People are purchasing souvenirs from a vendor.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: Purchasing souvenirs cannot be done at the same time as walking in a street.\nThe answer is no.\n[QUESTION] Premise: \"A singer in a black shirt is playing in a band.\"\nBased on this premise, can we conclude that the hypothesis \"The singer in the band is wearing black.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\nWearing black is another way to say in a black shirt.\nThe answer is yes.\nQ: Premise: \"A guy walking up the stairs holding a briefcase and a book.\"\nBased on this premise, can we conclude that the hypothesis \"A man is walking up the stair with his material to teach a class.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: A man can have a book and briefcase for things other than to teach a class.\nThe answer is it is not possible to tell.\nQUESTION: If \"Outdoor tables on a sunlit street are blocked off by red and white tape.\" does that mean that \"The tables are set up and street has been taped off for a block party.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: The tables may have been set up for something other than a block party.\nThe answer is it is not possible to tell.\nQUESTION: Given the sentence \"A grandfather is holding his grandson while pushing a stroller at a baseball game.\" is it true that \"A grandfather took his granson and son to the game.\"?\n\nLet's solve it slowly:",
"role": "user"
},
{
"content": "A grandfather is holding his grandson while pushing a stroller at a baseball game does not indicate that a grandfather took his granson and son to the game.\nThe answer is it is not possible to tell.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_80041
|
[
{
"content": "Teacher:In this task, you're given a fill-in-the-blank question that contains two object names. Additionally, you're given one answer which is one of the objects present in the question. In this task, you need to minimally change the given question so that the answer flips to another object in the question. Remember the question has to be about both objects which are related but different; for example, \"trophy\" and \"suitcase\". This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"small\" to \"big\"). You should not change any content in the given question beyond a word or two, i.e., the trigger word/phrase. The expected answer to your question must not be associated with just the trigger word; instead, it should depend on the context present in the question. The expected answer should not be ambiguous. For your question, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. In your generated question, retain the object names from the input question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. The two objects should be used ONCE in your question. Here is a list of attributes and associated contrastive words that may help write contrastive trigger words. Note that contrastive trigger words help in flipping the label.\n| Attribute | triggerword | contrastive triggerword | \n| age | old | new | \n| altitude | low | high |\n| area | small | vast | \n| brightness | dark | light | \n| clarity | obscure | clear | \n| cleanness | dirty | clean | \n| complexity | simple | complex | \n| cost | cheap | expensive |\n| density | sparse | dense |\n| depth | shallow | deep |\n| distance | near | far | \n| electric conductivity | low | high |\n| flexibility | rigid | flexible |\n| granularity | fine | coarse | \n| hardness | soft | hard | \n| length | short | long | \n| magnitude | small | large | \n| mass | small | large | \n| odor | weak | strong | \n| pressure | low | high | \n| resistance | low | high | \n| shape | round | sharp |\n| shape | flat | spiky |\n| size | small | large | \n| sound | quiet | loud | \n| sound pitch | low | high | \n| speed | slow | fast | \n| stability | unstable | stable | \n| strength | weak | strong | \n| temperature | low | high | \n| texture | smooth | rough | \n| thermal conductivity | low | high |\n| thickness | thin | thick | \n| volume | small | large |\n| weight | light | heavy | \n| width | narrow | wide | \n| location | in | out |\n| location | up | down |\n| location | above | below |\n| location | on | off |\n| location | to | from |\n\nTeacher: Now, understand the problem? Solve this instance: Context Word: night. \nQuestion: The owl flew into the night to hunt for food to bring back to her nest. She was glad the _ was plentiful. \nAnswer: food.\nStudent:",
"role": "user"
},
{
"content": "The owl flew into the night to hunt for food to bring back to her nest. She was glad the _ was high.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_79169
|
[
{
"content": "Teacher:In this task, you're given a fill-in-the-blank question that contains two object names. Additionally, you're given one answer which is one of the objects present in the question. In this task, you need to minimally change the given question so that the answer flips to another object in the question. Remember the question has to be about both objects which are related but different; for example, \"trophy\" and \"suitcase\". This task typically involves replacing one word i.e., the 'trigger word' with its antonym (e.g., changing from \"small\" to \"big\"). You should not change any content in the given question beyond a word or two, i.e., the trigger word/phrase. The expected answer to your question must not be associated with just the trigger word; instead, it should depend on the context present in the question. The expected answer should not be ambiguous. For your question, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. In your generated question, retain the object names from the input question. Avoid repeating the same style or phrase in generating your modified question e.g. this task can be always solved using a simple negation i.e. by adding not, never, etc. Instead, try to increase the word diversity. Your question must contain at least 15 and at most 30 words. Your question must have at least 70% overlapping words with the given question. You must utilize the given context word while writing the question. Your question must contain only one blank. The two objects should be used ONCE in your question. Here is a list of attributes and associated contrastive words that may help write contrastive trigger words. Note that contrastive trigger words help in flipping the label.\n| Attribute | triggerword | contrastive triggerword | \n| age | old | new | \n| altitude | low | high |\n| area | small | vast | \n| brightness | dark | light | \n| clarity | obscure | clear | \n| cleanness | dirty | clean | \n| complexity | simple | complex | \n| cost | cheap | expensive |\n| density | sparse | dense |\n| depth | shallow | deep |\n| distance | near | far | \n| electric conductivity | low | high |\n| flexibility | rigid | flexible |\n| granularity | fine | coarse | \n| hardness | soft | hard | \n| length | short | long | \n| magnitude | small | large | \n| mass | small | large | \n| odor | weak | strong | \n| pressure | low | high | \n| resistance | low | high | \n| shape | round | sharp |\n| shape | flat | spiky |\n| size | small | large | \n| sound | quiet | loud | \n| sound pitch | low | high | \n| speed | slow | fast | \n| stability | unstable | stable | \n| strength | weak | strong | \n| temperature | low | high | \n| texture | smooth | rough | \n| thermal conductivity | low | high |\n| thickness | thin | thick | \n| volume | small | large |\n| weight | light | heavy | \n| width | narrow | wide | \n| location | in | out |\n| location | up | down |\n| location | above | below |\n| location | on | off |\n| location | to | from |\n\nTeacher: Now, understand the problem? Solve this instance: Context Word: physical. \nQuestion: The doctor told the man a physical was not necessary for the insurance policy, because the _ previously was still valid. \nAnswer: physical.\nStudent:",
"role": "user"
},
{
"content": "The doctor told the man a physical was not necessary for the insurance policy, because the _ was still in good standing.",
"role": "assistant"
}
] |
flan_v2
|
flan_v2_82941
|
[
{
"content": "Given the task definition, example input & output, solve the new input case.\nIn this task, you're given a statement and three sentences as choices. Your job is to determine the neutral choice based on your inference from the statement and your commonsense knowledge. The neutral choice is a sentence that neither agrees nor disagrees with the statement. Indicate your answer as '1', '2', or '3', corresponding to the choice number of the selected sentence. If sentence X agrees with sentence Y, one's correctness follows from the other one. If sentence X disagrees with sentence Y, they can not be correct at the same time.\nExample: Statement: Next to the MGM Grand you will find M and M World, four stories of merchandise and memorabilia dedicated to the candy that doesn't melt in your hand. Choices: 1. The candy has many fans who love its attractions. 2. There's four stories of memorabilia dedicated to a candy. 3. That particular candy melts and becomes difficult to eat.\nOutput: 1\nThe candy may or may not be popular and the first choice is correct. Based on the statement, candy doesn't melt and there's four stories of memorabilia dedicated to a candy. So the second choice agrees with the statement and the third choice disagrees with the statement.\n\nNew input case for you: Statement: Some crystal ball. Choices: 1. A crystal ball from a set of multiple crystal balls. 2. No crystal ball of the set of crystal balls. 3. Some crystal ball you have there.\nOutput:",
"role": "user"
},
{
"content": "3",
"role": "assistant"
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.