Datasets:

Alignment-Lab-AI

/

english-flan

like 0

[ { "from": "human", "value": "Given an input stream, the objective of this task is to classify whether words in the stream are grammatically correct or not. The input to this task is a stream of words, possibly from captions generated by a speech-to-text engine, and the output is a classification of each word from the labels (reason) = [NO_DIFF (correct), CASE_DIFF (case error), PUNCUATION_DIFF (punctuation error), CASE_AND_PUNCUATION_DIFF (both case and punctuation error), STEM_BASED_DIFF (stem word error), DIGIT_DIFF (digit error), INTRAWORD_PUNC_DIFF (intra-word punctuation error), and UNKNOWN_TYPE_DIFF (an error that does not corrrespond to the previous categories)].\n\n[\"we're\", 'standing', 'in', 'the', 'main', 'aisle', 'of', \"what's\", 'known', 'as', 'the', 'Basilica', 'of', 'Maxentius', 'and', 'Constantine', 'and', 'even', \"what's\", 'left', 'is', 'just', 'huge', \"it's\", 'yeah', \"it's\", 'massive', 'scale', 'here', 'is', 'to', 'just', 'overwhelm', 'you', 'with', 'the', 'power', 'of', 'the', 'engineering', 'and', 'the', 'architecture', 'and', 'the', 'power', 'of', 'the', 'Emperor', 'that', 'niche', 'is', 'where', 'the', 'famous', 'head', 'and', 'limbs', 'of', 'Constantine', 'were', 'found', 'we', 'love', 'it', 'in', 'archaeology', 'our', 'history', 'and', 'we', 'actually', 'find', 'the', 'work', 'of', 'art', 'in', 'situ', 'so', 'we', 'actually', 'have', 'the', 'original', 'architectural', 'location', '', 'we', 'actually', 'have', 'the', 'architecture', 'this', 'was', 'started', 'by', 'the', 'Emperor', 'Maxentius']\n['NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'UNKNOWN_TYPE_DIFF', 'UNKNOWN_TYPE_DIFF', 'INTRAWORD_PUNC_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'UNKNOWN_TYPE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF']\n\n['a', 'circle', 'with', 'area', '81', 'pi', 'has', 'a', 'sector', 'with', 'a', '350-degree', 'central', 'angle', 'so', 'this', 'whole', 'sector', 'right', 'over', 'here', 'that', 'shaded', 'in', 'this', 'kind', 'of', 'pale', 'orange', 'LOH', 'color', 'that', 'has', 'a', 'that', 'has', 'a', '350-degree', 'central', 'angle', 'so', 'you', 'see', 'the', 'central', 'angle', \"it's\", 'a', 'very', 'large', 'angle', \"it's\", 'going', 'all', 'the', 'way', 'around', 'all', 'the', 'way', 'around', 'like', 'that', 'and', 'they', 'asked', 'us', 'what', 'is', 'the', 'area', 'of', 'the', 'sector', 'so', 'we', 'just', 'need', 'to', 'realize', '', 'the', 'ratio', 'between', 'the', 'area', 'of', 'the', 'sector', 'area', 'of', 'sector', 'the', 'area', 'the', 'ratio', 'between', 'the', 'area', 'of']\n['CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'UNKNOWN_TYPE_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'STEM_BASED_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF']\n\n['hey', \"it's\", 'Becca', 'and', 'this', 'is', 'temperance', 'part', '2', 'and', 'in', 'this', 'video', \"I'll\", 'be', 'talking', 'more', 'about', 'how', 'exactly', 'over', 'the', 'course', 'of', 'the', '1830s', 'until', 'mostly', 'the', '1860s', 'the', 'temperance', 'movement', 'took', 'root', 'in', 'America', 'and', 'how', 'it', 'became', 'this', 'national', 'phenomenon', 'so', 'a', 'lot', 'of', 'it', 'had', 'to', 'do', 'with', 'temperance', 'societies', 'so', 'in', 'the', 'last', 'video', 'I', 'mentioned', 'that', 'the', 'American', 'Temperance', 'Society', 'was', 'founded', 'in', '1826', 'so', \"that's\", '1826', 'but', 'the', 'American', 'Temperance', 'Society', 'really', 'was', 'this', 'group', 'of', 'upper-class', 'northern', 'white', 'dudes', 'saying', 'oh', 'well', 'we', 'should', 'probably', 'make', 'sure', 'that', 'people', \"don't\", 'drink']\n" }, { "from": "gpt", "value": "['NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'CASE_AND_PUNCUATION_DIFF', 'CASE_DIFF', 'DIGIT_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_AND_PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_AND_PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'CASE_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'CASE_AND_PUNCUATION_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF', 'PUNCUATION_DIFF', 'NO_DIFF', 'NO_DIFF', 'NO_DIFF']\n\n" } ]

[ { "from": "human", "value": "Definition: In this task, you're given the title of a story consisting of five sentences, numbered 1 through 5. Your job is to arrange the sentences in order to make a story that makes complete sense and is apt for the title. Indicate your answer using the number of the sentences in order, such as '34152'.\nInput: Title: Popsicle stick. Sentence 1: She threw the used stick in the bathroom garbage. Sentence 2: Kim was eating a popsicle. Sentence 3: She turned off the light and left. Sentence 4: She returned later to find ants all over the place. Sentence 5: She hadn't realized they would find the stick in the bathroom.\nOutput:" }, { "from": "gpt", "value": "21345" } ]

[ { "from": "human", "value": "The task is to generate text based of an event. For the given event, there will be a person who does the action in the event (usually PersonX). Your task is to write that persons emotional reaction to the event, i.e. how that person feels after doing the action.\nQ: PersonX makes a clean break\nA: " }, { "from": "gpt", "value": "free" } ]

[ { "from": "human", "value": "Given a story, answer the question about the story. The question is the last sentence in the input. The story has 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.\nQ: Oliver entered the dining_room. William entered the dining_room. The grapefruit is in the blue_bathtub. William exited the dining_room. Oliver moved the grapefruit to the red_crate. Oliver exited the dining_room. William entered the dining_room. Where is the grapefruit really?\nA: " }, { "from": "gpt", "value": "red_crate" } ]

[ { "from": "human", "value": "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, positions of two consecutive words have been swapped. You need to output the position of the swaped words. e.g. in the sentence 'Seattle has nice a weather', the word 'a' and 'nice' have been swapped. These words are at 3rd and 4th position respectively. So, the output should be (3, 4). Note that the index of first word is 1.\n\nI a am professional dancer.\nSolution: (2,3)\nWhy? words 'a' and 'am' have been swapped. The correct sentence would be 'I am a professional dancer.'. Since the position of 'a' is 2 and 'am' is 3, the answer is (2,3).\n\nNew input: Several surf boarders at city a wave pool\nSolution:" }, { "from": "gpt", "value": "(5, 6)" } ]

[ { "from": "human", "value": "Detailed Instructions: In this task you will be given a list of integers. You should round each integer to the nearest tens place. That means you should round the number to the nearest multiple of 10.\nProblem:[-640, -128, 40, 842, -412, 713, 676, -541]\nSolution:" }, { "from": "gpt", "value": "[-640, -130, 40, 840, -410, 710, 680, -540]" } ]

[ { "from": "human", "value": "Detailed Instructions: In this task, you're given the beginning and the middle of a three-part story. Your job is to complete the short story by writing a probable ending. Generated sentences must be short, have fewer than 10 words, and be simple as if narrating to a child. Avoid using any irrelevant extra information when creating the ending, and use names instead of pronouns (e.g. he / she) wherever possible.\nQ: Beginning: My body started to feel weak throughout the week. Middle: I decided to perform in the concert anyhow.\nA:" }, { "from": "gpt", "value": "The audience cheered for me." } ]

[ { "from": "human", "value": "In this task, you will be presented with a passage and have to answer a question based on your understanding of the events inferred from the passage. Among the entities, try to find the best entity that is most likely to fill in \"_\" and classify the answers based on options.\n\nInput: Consider Input: (CNN) Authorities missed an opportunity a decade ago to stop a key ISIS operative thought to be behind the Paris and Brussels attacks, a former Belgian intelligence officer says. Instead, Andre Jacob, who at the time was the head of the anti-terrorism unit for Belgian intelligence, says that Oussama Atar, believed by French authorities to be the elusive \"Abu Ahmad,\" was incarcerated in multiple Iraqi detention centers where he became further radicalized. The Belgian-Moroccan national, now 32, would years later introduce his own family -- including his cousins, the El Bakraoui brothers who carried out the Brussels attacks -- to his extremist ideologies, according to French and Belgian authorities.Oussama Atar is wanted by authorities in connection with Paris, Brussels terror attacksAndre Jacob, a retired anti-terror expert met him in 2006; says there was an opportunity to stop Atar a decade ago \n Questions:He says _ explained his injuries were the result of experimenting with grenades but insisted he was not taking part in military training. (A) CNN (B) ISIS (C) Paris (D) Brussels (E) Belgian (F) Andre Jacob (G) Oussama Atar (H) French (I) Abu Ahmad (J) Iraqi (K) Moroccan (L) El Bakraoui\n\nOutput: (G)\n\n\nInput: Consider Input: (CNN) -- News of Angelina Jolie's decision to undergo a prophylactic double mastectomy has instantly increased awareness of hereditary forms of cancer caused by mutations in the BRCA1 and BRCA2 genes. While the BRCA1 and BRCA2 genes were discovered in the mid-1990s, genetic testing for the genes is increasingly available. Jolie's case highlights the importance of knowing one's family history and learning one's cancer risks in order to address them proactively. Everyone has the BRCA1 and BRCA2 genes. We have two copies of each gene and get one each from our mother and father. They play a role in protecting the body against the development of cancer.Everyone has BRCA1 and BRCA2 genes; a mutation can show increased cancer riskNot everyone needs to be tested for the gene mutationGenetic counselors and other providers can help determine whether to test and when \n Questions:A positive _ result gives a woman a 60% to 80% lifetime risk of breast cancer and a 30% to 45% lifetime risk of ovarian cancer. (A) CNN (B) Angelina Jolie (C) BRCA1 (D) BRCA2 (E) Jolie\n\nOutput: (C)\n\n\nInput: Consider Input: Kiev, Ukraine (CNN) The setting was a Manhattan restaurant, and after 25 minutes what allegedly emerged was a pro-Russian peace plan for Ukraine that its author believes may have ended up in the White House. In a CNN interview, Ukrainian lawmaker Andrii Artemenko said he discussed his left-field proposal for Ukraine in January with US President Donald Trump's personal lawyer, Michael Cohen, who offered to deliver the plan to the Trump administration. The exact details of the plan are unclear, yet reports have suggested it revolves around leasing Crimea -- annexed by Russia from Ukraine in 2014 -- to Moscow for 50 to 100 years. In exchange, Russia would withdraw its troops from the separatist regions in Ukraine's war-torn east.Ukrainian politician says Trump lawyer Michael Cohen offered to deliver peace plan to Michael FlynnCohen says he met with the politician but denies discussing Ukraine peace proposal \n Questions:Cohen told CNN in a text message that although he had dinner with _, they never discussed peace in Ukraine. (A) Kiev (B) Ukraine (C) CNN (D) Manhattan (E) Russian (F) White House (G) Ukrainian (H) Andrii Artemenko (I) US (J) Donald Trump (K) Michael Cohen (L) Trump (M) Crimea (N) Russia (O) Moscow (P) Michael Flynn (Q) Cohen\n\n" }, { "from": "gpt", "value": "Output: (H)\n\n\n" } ]

[ { "from": "human", "value": "Given a sentence, fill out the missing word with a 'no' or a number (between zero and ten). You should write the numbers with english alphabet, like: four instead of 4.\n\nInput: Consider Input: Most health professionals recommend approximately ____ hours of sleep each night.\n\nOutput: eight\n\n\nInput: Consider Input: HOD usually shows up as an acute lameness, often seeming to affect all ____ legs simultaneously.\n\nOutput: four\n\n\nInput: Consider Input: Many churches have ____ windows on each side of the nave, numbers some consider holy.\n\n" }, { "from": "gpt", "value": "Output: seven\n\n\n" } ]

[ { "from": "human", "value": "In this task, you're given a review from Amazon's food products. Your task is to generate a short summary of the given review in the input. Note that you don't need to write a complete sentence as a summary.\n\nEx Input:\nI have been drinking Tully's Kona for the past 2 years, but with the price increase of kona, I needed to find something less expensive. After trying numerous kcups, this Mahogany is just as good as the Kona, with a full coffee flavor, and a hint of caramel. I am happily converted.\n\nEx Output:\nGreat coffee\n\n\nEx Input:\nSo I am a huge Chocolate Peanut Butter freak, and have been looking for a peanut butter cup cocoa for a while. I finally broke down and ordered this after a few months hemming and hawwing about it. Now I aadmit to not reading the directions the first cup and at first was like wow slightly chocolate water and added a few more spoonfuls of the mix to my cup and it improved but was not quite what i expected and this was made with water(I was at work and had little choice) The next day I deceided to try it again at home in my hot cocoa machine with milk and there was a GREAT improvement!! So as a result I'm going to try an experiment tonight and make a shake in the blender with the mix!!! I said im a peanut butter cup freak!!!\n\nEx Output:\nPretty good\n\n\nEx Input:\nI like the taste of these but they are inconsistent in texture (some are really really hard, while others are what you would expect). You have to be careful with the microwaving part, but even when you are, it's hard to get consistent results. They also could be a little spicier for my taste.\n\nEx Output:\n" }, { "from": "gpt", "value": "Not bad, but hard to get right\n\n\n" } ]

[ { "from": "human", "value": "Q: You are given a conversation between two people. 'Person1:' and 'Person2:' are used to separate their respective dialogues. Your task is to classify the conversation either convey 'No emotion' or 'Happiness' by providing '1' and '0', respectively.\n Person1: We should keep Frank at arm's length . \n Person2: Yeah . He's known as a sly dog . He's done many people in . \n Person1: He hits below the belt . \n Person2: And he may cash in on people whenever chances are provided . \nA:" }, { "from": "gpt", "value": "0" } ]

[ { "from": "human", "value": "Detailed Instructions: Given a premise and two alternatives, choose the alternative that is a more plausible cause or effect of the situation described by the premise. The input format is \"premise\n(1)alternative_1(2)alternative_2\", the output should either be \"1\" or \"2\" based on your judgment.\nQ: I hung the wet linen on the outdoor clothesline.\n(1)The linen dried.(2)The linen stained.\nA:" }, { "from": "gpt", "value": "1" } ]

[ { "from": "human", "value": "In this task, you are given a sentence or phrase in Xhosa. You must translate it to English in a way that is equivalent in terms of meaning and grammatically correct.\n\n[Q]: Njengoko ingqayi zenqanawa enamaphiko enkulu zivelisiwe kwixa elizayo, loluhlobo lwentsimbi eyasu-yasu lolungiso ngendlela eyiyo lodwa oluza kusebenziseka.\n[A]: As larger hydrofoil vessels are developed in the future only this type of foil system will be employed.\n\n\n[Q]: Yiplatfom yeplanga okanye yelitye eyenziwe kwindonga zomlambo okanye ezibukweni ukunikezela ngendawo yokulala kwinqanawa ukulayisha okanye ukothula abakhweli okanye imithwalo. Ngokufanayo nesithulelo senqanawa nangona indawo yokulayishela nokothula iinqanawa nayo idla ngokwenziwa ngamaplanga ngeli lixa isothulelo sona sisenziwa ngamatye.\n[A]: A wood or stone platform constructed along the banks of a river or in a harbour to provide berths for vessels to load and discharge passengers and cargo. Similar to quay although a wharf is usually made of wood whilst a quay is built from stone.\n\n\n[Q]: Yi-arhente enoxanduva lokuqinisekisa ukuba i-V&V iyenziwa kwimodeli echaziweyo okanye kwimfaniso. [DIS]\n[A]:" }, { "from": "gpt", "value": "The agency responsible for ensuring V&V is performed on a specific model or simulation. [DIS]\n\n\n" } ]

[ { "from": "human", "value": "Detailed Instructions: Given an trivia question precisely answer the question with a word/phrase/name. External resources such as Wikipedia could be used to obtain the facts.\nProblem:What was John Napier famous for inventing?\nSolution:" }, { "from": "gpt", "value": "logarithms" } ]

[ { "from": "human", "value": "Definition: In this task, you are given two facts, and a multiple-choice question. Based on the given facts, answer the question with index of the correct option (e.g, \"A\").\nInput: Fact1: Spores may be dispersed by moving water, wind, or other organisms., Fact2: Humans are complex organisms., Question: what can disperse spores? (A) alpacas (B) insects (C) humans (D) wind (E) honeybees (F) seeds (G) fungi (H) ferns\nOutput:" }, { "from": "gpt", "value": "C" } ]

[ { "from": "human", "value": "In this task you will be given a list of integers. You should only return an integer if the first digit is the same as the last digit in the number. If an integer has a single digit, then it should be returned. If there are no integers that start and end with the same digit then an empty list (\"[]\") should be returned.\n\n[EX Q]: [-373, 256, 92, 278, 1, -676, -161, 601, -459, 652, 890, 330, 360, -635, 922, 169, -528, 560, 178]\n[EX A]: [-373, 1, -676, -161]\n\n[EX Q]: [-729, 393, -602, -511, -133, 668, 919, 508, -803, -498, -189, 509, -405, 138, 974, 771, 601, 931]\n[EX A]: [393, 919]\n\n[EX Q]: [-494, 598, -245, 225, -795, -353, -435, 138, 713, 688, 420, -249, 391, -681, -469, 440, 86, -617, 203, -950, 203]\n[EX A]:" }, { "from": "gpt", "value": "[-494, -353]\n\n" } ]

[ { "from": "human", "value": "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 alphabetical elements in the given list in order. Assume the position of the 1st element to be 1. Return -1 if no alphabetical element is in the list.\n\n[Q]: ['9489', '8887', 't', 'Z', 'M']\n[A]: 3, 4, 5\n\n\n[Q]: ['i', '5931', '2695', '3655', 'i', '3795', '817', 'I', 'a', '3457', 'F', '185', 'v', '8225', '823', '5727', '6295', 'r', '285', 'x', '8063', 'T']\n[A]: 1, 5, 8, 9, 11, 13, 18, 20, 22\n\n\n[Q]: ['8023', '9673', 'p', 'P', '8987', '2385', '4025', '2241', '7653', '3349', 'T', 'w', '4855', 'u', '9737', 'f', 'R', '5139', 'g', '863', 'i', '349', '2137', '9343', 'M', '3689', '4707', '5197', '5587', 'b', 'P']\n[A]:" }, { "from": "gpt", "value": "3, 4, 11, 12, 14, 16, 17, 19, 21, 25, 30, 31\n\n\n" } ]

[ { "from": "human", "value": "Given a sentence, generate a most likely context or previous statement. The previous statement should be relevant to the given statement.\nQ: Someone rubs his hands together, inhales through them, and dashes off.\nA: " }, { "from": "gpt", "value": "The horses race down the track." } ]

[ { "from": "human", "value": "Given the prompt and a response, classify the them to \"yes\" if response is \"yes, and\" type. Otherwise classify it as \"no\". \"Yes, and\" is a rule-of-thumb in improvisational comedy that suggests that a participant in a dialogue should accept what another participant has stated (\"Yes\") and then expand on that line of thought or context (\"and...\"). 1 In short, a \"Yes, and\" is a dialogue exchange in which a speaker responds by adding new information on top of the information/setting that was constructed by another speaker. Note that a \"Yes, and\" does not require someone explicitly saying 'yes, and...' as part of a dialogue exchange, although it could be the case if it agrees with the description above. There are many ways in which a response could implicitly/explicitly agree to the prompt without specifically saying 'yes, and...'. \n\n[Q]: Prompt: You guys are going to want to take a moment and say a few words to your poster before I put it in the recycling bin. \n Response: I think that's a great compromise. You can come in any time you want to see the poster.\n[A]: no\n\n\n[Q]: Prompt: When I woke up, I meditated and I did my affirmations. I didn't watch TV. \n Response: I said a full rosary, looked out the window for awhile and I had a cup of coffee.\n[A]: yes\n\n\n[Q]: Prompt: Do we even want to go back to the big world? \n Response: That is the question, isn't it? For so long, we didn't even know that we were small.\n[A]:" }, { "from": "gpt", "value": "yes\n\n\n" } ]

[ { "from": "human", "value": "Teacher:In this task, you are given a sentence with a missing word that can be an object, a person, and/or an action. Fill in the blank with a plausible word. Although each sentence has many correct answers, you only have to write one answer.\nTeacher: Now, understand the problem? Solve this instance: PersonX takes care of PersonY ___\nStudent:" }, { "from": "gpt", "value": "car" } ]

[ { "from": "human", "value": "Detailed Instructions: Given an entity, a before event, an after event, and an attribute related to the entity, generate a sentence as output. Your sentence should show the changes in the attribute of the entity.\nQ: entity: tank cover \nbefore: on tank \nafter: lifted off tank \nattr: location\nA:" }, { "from": "gpt", "value": "location of tank cover was on the tank before and lifted off the tank afterwards" } ]

[ { "from": "human", "value": "In this task you are given a sentence pair from wikipedia that have high lexical overlap. If the sentences have the same meaning and are just paraphrases of each other label them as \"Paraphrase\" , if not label them as \"Not paraphrase\". The two sentences are seperated by a new line.\n\nThere are quite a number of festivals and traditions in Spain ( Catalonia ) .\nIn Catalonia ( Spain ) there are a number of festivals and traditions ." }, { "from": "gpt", "value": "Paraphrase" } ]

[ { "from": "human", "value": "You are given a short poem which is written by a kid. Your task is to predict if the kid is in elementary school or high school. Anyone who is from grade 1st to 6th-grade will be considered as in elementary school, and 7th to 12th-grade kids will be considered as in high school. There are only two possible outputs, i.e., elementary and high. All inputs have at least one output and it cannot have both categories at a time.\n\nLet me give you an example: he look into your eye that same look just take your breathe away you feel at that moment that he be definitely the one for you but just when you realize that just as fast a he take your breathe away he take your heart and break it into tiny little piece and watch it burn\nThe answer to this example can be: high\nHere is why: The poem is long and linguistically well structured, and the prediction is correct.\n\nOK. solve this:\nwhen i awake one morning an otter snooze on my head i ask what be you do there it look at me and say i ca n't really talk right now i 'm in my dream home swimming in the sea and my buddy be all with me\nAnswer:" }, { "from": "gpt", "value": "elementary" } ]

[ { "from": "human", "value": "Detailed Instructions: In this task, you will be presented with a context from an academic paper and you have to write an answerable question based on the context. Your questions can be extractive, abstractive, or yes-no questions.\nQ: Furthermore, we employ two different parsers for comparison: 1) the PCFGLA-based parser, viz. Berkeley parser BIBREF5 , and 2) a minimal span-based neural parser BIBREF6 .\nA:" }, { "from": "gpt", "value": "What is the baseline model for the agreement-based mode?" } ]

[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task you will be given a string that only contains single digit numbers spelled out. The input string will not contain spaces between the different numbers. Your task is to return the number that the string spells out. The string will spell out each digit of the number for example '1726' will be 'oneseventwosix' instead of 'one thousand seven hundred six'.\n\nninezeroeightfourtwo\nOutput:" }, { "from": "gpt", "value": "90842" } ]

[ { "from": "human", "value": "Definition: In this task, you're given a context, a question, three options, and an answer. Your task is to classify whether the given answer is correct or not by providing 'Yes' or 'No', based on the context with commonsense reasoning about social situations.\nInput: Context: Skylar tilted Kendall's head back to whisper the secret. \n Question: What will Kendall want to do next? \n Options: (A) Ignore Skylar (B) Run away from Skylar (C) Watch for Skylar's response \n Answer: B\nOutput:" }, { "from": "gpt", "value": "No" } ]

[ { "from": "human", "value": "Q: In this task, you are given a sentence. You must judge whether a single noun or verb has been replaced with another word with the same part of speech. The inversion would result in the sentence sounding unnatural, So unnatural sentences will be considered changed. Label the instances as \"Original\" or \"Changed\" based on your judgment.\nJosie Galloway was not piqued in the slightest that she would be interacting with the most handsome and intriguing man in a hundred square miles .\nA:" }, { "from": "gpt", "value": "Original" } ]

[ { "from": "human", "value": "Detailed Instructions: In this task you're given a question and you have to paraphrase the question to create the output question while retaining the meaning of the original question.\nQ: How do darkroom chemicals work?\nA:" }, { "from": "gpt", "value": "What are darkroom chemicals?" } ]

[ { "from": "human", "value": "instruction:\nIn this task, you are given a news article. Your task is to classify the article to one out of the four topics 'World', 'Sports', 'Business', 'Sci/Tech' if the article's main topic is relevant to the world, sports, business, and science/technology, correspondingly. If you are not sure about the topic, choose the closest option. Note that URLs in the text have been replaced with [Link].\nquestion:\nEngland stutter for Zimbabwe win England beat Zimbabwe by five wickets in the opening one-day international.\nanswer:\nWorld\n\n\nquestion:\nData loss hits Russia crash probe Russian officials remain baffled after examining the black boxes from Tuesday's mystery double air crash.\nanswer:\nWorld\n\n\nquestion:\nWashington Baseball at Risk, MLB May Seek Bids WASHINGTON (Reuters) - Washington, D.C., Mayor Anthony Williams on Wednesday said the deal to bring baseball back to the U.S. capital was close to dead after the city council changed the plan to require private financing, a move Major League Baseball called unacceptable.\nanswer:\n" }, { "from": "gpt", "value": "Sports\n\n\n" } ]

[ { "from": "human", "value": "Teacher:In this task, you are given a pair of action statements. Your task is to check if you can conclusively identify which statement is less ethical or not. Answer: 'no' if one of the statements is less ethical, and 'yes' otherwise.\nTeacher: Now, understand the problem? Solve this instance: ACTION1: wanting my bf to move with me ACTION2: acting salty towards my friend for choosing a different school\nStudent:" }, { "from": "gpt", "value": "no" } ]

[ { "from": "human", "value": "Detailed Instructions: You are given a sentence in Spanish. Your job is to translate the Spanish sentence into English.\nProblem:No estoy realmente interesada en los famosos por los famosos mismos.\nSolution:" }, { "from": "gpt", "value": "I'm not really interested in the celebrity themselves." } ]

[ { "from": "human", "value": "TASK DEFINITION: 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.\nPROBLEM: 5, ['Z', 'K', 's', '6337', 'J', 'x', 'm', '1421', '5599', '7047', 'l', '2125', '1273', '5243']\n\nSOLUTION: x, m, 1421, 5599, 7047, l, 2125, 1273, 5243\n\nPROBLEM: 2, ['1735', '169', '1269', '9529', '3539', 'L', 'C', 'I', '5187', 'p', 'D', 'Z', 'd', '5575', 'n', 'Y', 'b', 'v', '3405', '8107', 'A', 'N', '8969', 'w', '4533']\n\nSOLUTION: 1269, 9529, 3539, L, C, I, 5187, p, D, Z, d, 5575, n, Y, b, v, 3405, 8107, A, N, 8969, w, 4533\n\nPROBLEM: 1, ['4303', '211', 'c', '4207', 'f', '2259', 'G', 'e', '869', '4725', '4383', 'E', 'v', '8445', '8699', '2903', 'b', 'u', '1279', 'k', 'A', 'p', 'Q', 'v', '3991', '5151', '1269']\n\nSOLUTION:" }, { "from": "gpt", "value": "211, c, 4207, f, 2259, G, e, 869, 4725, 4383, E, v, 8445, 8699, 2903, b, u, 1279, k, A, p, Q, v, 3991, 5151, 1269\n\n" } ]

[ { "from": "human", "value": "Detailed Instructions: In 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 seamlessly connects with the rest of the story, indicating your choice as 'a' or 'b'. If both sentences are plausible, pick the one that makes more sense.\nSee one example below:\nProblem: Title: 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: a\nExplanation: Marcus is buying clothes for a business event and not presenting an idea.\n\nProblem: Title: Stanley is Missing. Sentence 1: Stanley went to the park every day to play checkers. Sentence 2: One day he didn't show up. Sentence 3: His friends were worried. Sentence 4: They called Stanley's family to check on him. Choices: a. I didn't get my credits for participating due to early termination. b. Stanley had suffered a fall and was in the hospital.\nSolution:" }, { "from": "gpt", "value": "b" } ]

[ { "from": "human", "value": "instruction:\nIn this task, you are given a premise, a hypothesis, and an update. The premise sentence describes a real-world situation and is always assumed to be true. The hypothesis sentence describes an assumption or inference that you might make about that situation having read the premise. The update provides additional information about the situation that might weaken or strengthen the hypothesis. A weakener is a statement that weakens the hypothesis. It makes you much less likely to believe the hypothesis is true. A strengthener is a statement that strengthens the hypothesis. It makes you much more likely to believe the hypothesis is true. Your task is to output 'strengthener' or 'weakener' if the update strengths or weakens the hypothesis, respectively.\nquestion:\nPremise: PersonX celebrates PersonY 's day\nHypothesis: Because PersonX wanted make person y happy\nUpdate: They want them to return a favor\nanswer:\nweakener\n\n\nquestion:\nPremise: PersonX plans a party\nHypothesis: Because PersonX wanted be around people\nUpdate: PersonX is being paid by a client\nanswer:\nweakener\n\n\nquestion:\nPremise: PersonX feels a sharp sting\nHypothesis: PersonX then person x yells\nUpdate: PersonX was stung by a bullet ant.\nanswer:\n" }, { "from": "gpt", "value": "strengthener\n\n\n" } ]

[ { "from": "human", "value": "Definition: This task is about classifying the similarity of two sentences. The sentences can be classified as (a) SIMILAR - similar to each other, and (b) DISSIMILAR - not similar to each other. Sentences that have the same RDF relationship in terms of [subject, predicate, object] are similar to each other. The input is a list of two sentences and the output is either SIMILAR or DISSIMILAR.\nInput: ['There is a pub serving fast food in the city centre named The Waterman. This pub has a customer rating of 5 out of 5.', '250 Delaware Avenue has a floor area of 30853.8 square metres and has 12 floors.']\nOutput:" }, { "from": "gpt", "value": "DISSIMILAR" } ]

[ { "from": "human", "value": "Teacher: In this task, you are given a premise, a hypothesis, and an update. The premise sentence describes a real-world situation and is always assumed to be true. The hypothesis sentence describes an assumption or inference that you might make about that situation having read the premise. The update provides additional information about the situation that might weaken or strengthen the hypothesis. A weakener is a statement that weakens the hypothesis. It makes you much less likely to believe the hypothesis is true. A strengthener is a statement that strengthens the hypothesis. It makes you much more likely to believe the hypothesis is true. Your task is to output 'strengthener' or 'weakener' if the update strengths or weakens the hypothesis, respectively.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nPremise: PersonX seems interested\nHypothesis: PersonX then good activity\nUpdate: PersonX was a good student\nSolution: strengthener\nReason: If PersonX was a good student, it is more likely that PersonX would do good activities.\n\nNow, solve this instance: Premise: PersonX talks out of turn\nHypothesis: PersonX is seen as assertive\nUpdate: PersonX is trying to be the leader of the project\nStudent:" }, { "from": "gpt", "value": "strengthener" } ]

[ { "from": "human", "value": "In this task, answer 'Yes' if the frequency of the given word in the two sentences is equal, else answer 'No'.\n\nSentence1: 'a phone shows a video of a woman singing', Sentence2: 'a pan pizza with a thick crust on a cutting board with a knife'. Is the frequency of the word 'a' in two sentences equal?" }, { "from": "gpt", "value": "No" } ]

[ { "from": "human", "value": "Given a sentence, generate a most unlikely next statement. The next statement should not be logically relevant to the given context\n\nWomen walks to a a barn. people start playing beerpong in a party and a lot of people" }, { "from": "gpt", "value": "are taking boxing boxing gloves." } ]

[ { "from": "human", "value": "Definition: In this task, you're given a statement, and three sentences as choices. Your job is to determine which sentence clearly disagrees with the statement. Indicate your answer as '1', '2', or '3' corresponding to the choice number of the selected sentence.\nInput: Statement: She observed that institutionalizing new practices was just the beginning of the task. Choices: 1. The task involved far more than she initially anticipated. 2. She carefully noted how to skirt around the safeguards in order to complete her assignment. 3. She was good at observing and saw that more was required than just the basics.\nOutput:" }, { "from": "gpt", "value": "2" } ]

[ { "from": "human", "value": "In this task, based on the given context word, you are asked to create a pair of sentences each containing a blank (_) and their corresponding answer. The sentence pair should look similar, and should be about two related but different objects; for example \"trophy\" and \"suitcase\". Additionally, the two sentences must be different in terms of trigger words (e.g., \"small\" and \"big\") which express contrasting properties about the two objects. The answer must not be associated with the trigger word; instead, it should depend on the context present in twin sentences. Also, the answers should not be ambiguous. For each sentence, there should be an agreed upon answer to fill in the blank. Your generations should NOT contain potentially explicit, offensive, or adult content. Do not use animals and proper nouns (e.g., New York, Macbook, Jeff Bezos, McDonald's, ...) as your objects. Avoid repeating the same style or phrase in twin sentences. E.g., a contrasting sentence can always be created using simple negation i.e. by adding not, never, etc. Instead, try to increase diversity. Both twin sentences must contain at least 15 and at most 30 words. Twin sentences must have at least 70% overlapping words. You must utilize the given context word while writing the twin sentences. Each of the twin sentences must contain only one blank. Make sure that ObjectX and Y have the same number e.g. when ObjectX is singular, ObjectY must be singular, too. The two objects (ObjectX & ObjectY) should be used ONCE in each sentence. Here is a list of contrastive words that may be used as trigger words. You should create more such trigger words and use them in your twin sentences.\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: golfer." }, { "from": "gpt", "value": "Sentence 1: The golfer decided to buy new shoes, but not clubs, because his _ were worn. \nAnswer1: shoes. \nSentence 2: The golfer decided to buy new shoes, but not clubs, because his _ were newer. \nAnswer2: clubs." } ]

[ { "from": "human", "value": "Teacher:In this task, you will be presented with a question and you have to answer the question based on your knowledge. Your answers should be as short as possible.\nTeacher: Now, understand the problem? Solve this instance: When did this incident happen for which this politician representing this district known for its two major cities of Greenville and Spartanburg represented ?\nStudent:" }, { "from": "gpt", "value": "May 22 , 1856" } ]

[ { "from": "human", "value": "In this task, you need to generate an appropriate title for the given summary of some paragraph. The generated title must be short and should include the main topic of the given text. Your summary should be less than 20 words long.\nOne example is below.\nQ: For many Brazilians, Michel Temer's ascension to president was surprising. But as the first Brazilian president to have charges brought against him while in office, his arrest is less unexpected.\nA: Michel Temer: Brazil's arrested former president\nRationale: The output is a relevant title for the given passage as it highlights the main crux of the given text.\nQ: An inspection report has criticised the way the police deal with domestic violence in Northern Ireland.\nA:" }, { "from": "gpt", "value": "PSNI criticised over domestic violence handling" } ]

[ { "from": "human", "value": "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 public comment from online platforms. You are expected to classify the comment into two classes: sexual-explicit and non-sexual-explicit. A comment is considered sexual-explicit if it explicitly portrays sexual matters.\n\nComment: President lied under oath about consensual sex...\nNot the same thing as rape.\nSolution: Sexual-explicit\nWhy? This comment explicitly mentions \"consensual sex\" and \"rape\", and thus is sexual-explicit.\n\nNew input: Comment: liar\nSolution:" }, { "from": "gpt", "value": "Non-sexual-explicit" } ]

[ { "from": "human", "value": "In this task, you will be shown a short story with a beginning, two potential middles, and an ending. Your job is to choose the middle statement that makes the story incoherent / implausible by indicating 1 or 2 in the output. If both sentences are plausible, pick the one that makes less sense.\n\nBeginning: Sarah worked hard. Middle 1: Sarah wanted to buy a house. Middle 2: Sarah wanted to buy a candy. Ending: She didn't care about nothing but the money.\n2\n\nBeginning: Iris was carrying plates to the cupboard. Middle 1: Iris's decided to use them as a frisbee to throw them everywhere. Middle 2: Iris dropped a couple of plates and they broke. Ending: She cleaned them up carefully.\n1\n\nBeginning: Julie kept hearing things at night outside her window. Middle 1: Julie got scared that there was a raccoon outside her house trying to get in. Middle 2: Julie got scared that there was a burglar outside her house trying to get in. Ending: He cut the branch back and Julie could sleep again.\n" }, { "from": "gpt", "value": "1\n\n" } ]

[ { "from": "human", "value": "Detailed Instructions: In this task you will be given a list of integers. You should remove any integer that is not prime. A prime integer is an integer that is only divisible by '1' and itself. The output should be the list of prime numbers in the input list. If there are no primes in the input list an empty list (\"[]\") should be returned.\nQ: [41, 80, 307, 853, 809, 357, 829, 6, 981, 243, 607, 630, 363, 227, 455, 557, 694, 173, 523]\nA:" }, { "from": "gpt", "value": "[41, 307, 853, 809, 829, 607, 227, 557, 173, 523]" } ]

[ { "from": "human", "value": "Definition: In this task you will be given a list of numbers. You should remove any number that is not an integer (whole number). If every number is not an whole number then an empty list (\"[]\") should be returned. Otherwise, answer with the list of whole numbers separated by comma inside brackets.\nInput: [-96, -3.438, -28]\nOutput:" }, { "from": "gpt", "value": "[-96, -28]" } ]

[ { "from": "human", "value": "Detailed Instructions: Given a sentence, generate a new sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.\nQ: You would grow vegetables because you want food to eat.\nA:" }, { "from": "gpt", "value": "You would grind vegetables because you want food to use ." } ]

[ { "from": "human", "value": "This task is about creating an unanswerable question based on a given passage. Construct a question that looks relevant to the given context but is unanswerable. Following are a few suggestions about how to create unanswerable questions:\n(i) create questions which require satisfying a constraint that is not mentioned in the passage\n(ii) create questions which require information beyond what is provided in the passage in order to answer\n(iii) replace an existing entity, number, date mentioned in the passage with other entity, number, date and use it in the question\n(iv) create a question which is answerable from the passage and then replace one or two words by their antonyms or insert/remove negation words to make it unanswerable.\n\nPassage: Originally known as Buckingham House, the building at the core of today's palace was a large townhouse built for the Duke of Buckingham in 1703 on a site that had been in private ownership for at least 150 years. It was acquired by King George III in 1761 as a private residence for Queen Charlotte and became known as \"The Queen's House\". During the 19th century it was enlarged, principally by architects John Nash and Edward Blore, who constructed three wings around a central courtyard. Buckingham Palace became the London residence of the British monarch on the accession of Queen Victoria in 1837." }, { "from": "gpt", "value": "What is Buckingham Palace currently known as?" } ]

[ { "from": "human", "value": "Detailed Instructions: In this task, you're expected to write answers to questions involving multiple references to the same entity. The answer to the question should be unambiguous and a phrase in the paragraph. Most questions can have only one correct answer.\nProblem:Passage: In the early 1980s, teenagers Martin Asher and Matt Soulsby meet on a bus to Mont-Laurier, Quebec. Seemingly uncertain of their ultimate destination, the two talk about their plans for the future. When their bus breaks down, the two acquire a car from a nearby garage. While Martin is driving, a tire blows. Matt struggles to change the tire and Martin comments on how he and Matt are both about the same height, and kicks Matt into the path of an oncoming truck, killing both him and the driver. Taking Matt's guitar and clothes, he walks away singing in a voice similar to Matt's. \nTwenty years later, a successful FBI profiler, Illeana Scott, is summoned to help out the authorities in Montreal in apprehending a serial killer who assumes the identities of his victims, enabling him to travel undetected across North America. Martin's mother Rebecca claims to have seen her son alive and well on a ferry to Quebec City, leading to the body believed to have belonged to him being exhumed for forensic examination, and he becomes the primary suspect. Illeana, who has difficulty adjusting to her new surroundings and is distrusted by her local colleagues, interviews art dealer James Costa, an eyewitness who saw Asher kill his last victim. Costa makes a drawing of the killer and the authorities manage to track down the man's apartment, only to find a decaying corpse chained up in the ceiling. Illeana goes to Rebecca's house to question her about her son, and while snooping around discovers a hidden passageway behind a cabinet that leads to a secret room used to house young Martin, an unwanted and unstable younger child whom Rebecca neglected and saw as inferior to her elder son, whom Martin ultimately killed out of jealousy. Illeana is attacked by a hidden assailant, who escapes before she can identify him. \nQuestion: What is the first name of the person who takes the guitar and clothes?\nSolution:" }, { "from": "gpt", "value": "Martin." } ]

[ { "from": "human", "value": "Given a command in a limited form of natural language, provide the correct sequence of actions that executes the command to thus navigate an agent in its environment. A command can be broken down into many different actions. Actions are uppercase and are individual steps that serve as the building blocks for a command. For commands, 'left' and 'right' are used to denote the direction of an action. The word 'opposite' turns the agent backward in the specified direction. The word 'around' makes the agent execute an action while turning around in the specified direction. The word 'and' means to execute the next scope of the command following the previous scope of the command. The word 'after' signifies to execute the previous scope of the command following the next scope of the command. The words 'twice' and 'thrice' trigger repetition of a command that they scope over two times or three times, respectively. There are only six actions: 'I_LOOK', 'I_WALK', 'I_RUN', 'I_JUMP', 'I_TURN_LEFT', and 'I_TURN_RIGHT'. These actions respectively align with the commands 'look', 'walk', 'run', 'jump', 'turn left', and 'turn right'. Actions and commands do not have quotations in the input and output.\nQ: walk opposite right twice and jump right twice\nA: " }, { "from": "gpt", "value": "I_TURN_RIGHT I_TURN_RIGHT I_WALK I_TURN_RIGHT I_TURN_RIGHT I_WALK I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP" } ]

[ { "from": "human", "value": "Detailed Instructions: The provided file includes inquiries about restaurants, and we ask you to translate those to the Italian language. Please bear in mind the following guidlines while doing the translation: 1) We are looking for the most naturally written and formal form of each sentence in your language. We are *NOT* looking for colloquial forms of the sentence. We are looking for formal form which is how you would type your queries in a text-based virtual assistant. 2) The words between quotation marks *SHOULD NOT* be translated. We expect you to keep those values intact and include the quotation marks around them as well. 3) The fully capitalized words like DATE_0, or DURATION_0 *SHOULD NOT* be translated. Please keep them as they are in the translations. 4) Please do not localize measurement units like miles to kilometers during your translation. miles should be translated to its equivalent in your language. 6) Note the input is all lowercased except for special placeholders. Please do the same in your translations.\nProblem:look up a \" mexican \" restaurant for me .\nSolution:" }, { "from": "gpt", "value": "cerca un ristorante \" mexican \" per me." } ]

[ { "from": "human", "value": "Definition: You are given a sentence and a question in the input. The information provided in the sentence should be enough to answer the question. You're expected to write the correct answer. Do not use any facts other than those provided in the sentence.\nInput: Sentence: In her dream she tripped over a log and hurt her ankle. \nQuestion: What did Lizzie dream about?\nOutput:" }, { "from": "gpt", "value": "Tripping and hurting ankle." } ]

[ { "from": "human", "value": "Definition: In this task, you are given two simple actions (associated with \"A\", \"B\"). You must identify which action is considered less ethical. Do not generate anything else apart from one of the following characters: 'A', 'B'.\nInput: (A) rage quitting on my boss\n(B) reporting my cousin and her husband for identity theft\nOutput:" }, { "from": "gpt", "value": "A" } ]

[ { "from": "human", "value": "In this task, you're given context and an answer. Your task is to generate the question for this answer based on the given context with commonsense reasoning about social situations..\nQ: Context: Sydney turned Austin's heads red by tripping and dropping the expensive vase that day. \n Answer: sad\nA: " }, { "from": "gpt", "value": "How would Austin feel as a result?" } ]

[ { "from": "human", "value": "The task is to generate text based off of an event. For the given event, there will be a person who does the action in the event (usually PersonX). Your task is to write that persons intent behind doing the event, i.e. why did the person do that action.\nQ: PersonX wipes the ___ from PersonY's eyes\nA: " }, { "from": "gpt", "value": "to show love" } ]

[ { "from": "human", "value": "Instructions: You are given a target profession, and two sentences. Your task is to determine whether the second sentence is either a stereotype, anti-stereotype, or is unrelated with respect to the first sentence and the target. A stereotype is a widely held but oversimplified notion of a group of people. An anti-stereotype is an idea that goes against the widely held but oversimplified notion of a group of people. Sentences and targets are unrelated if there is no relevance between them.\nInput: Target: historian \nThe historian entered the library. She was curvy and gorgeous and laughed a great deal.\nOutput:" }, { "from": "gpt", "value": "anti-stereotype" } ]

[ { "from": "human", "value": "Teacher: 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.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\n['8129', 'a', '4245', '2391', 'Y', '7569']\nSolution: 8129, 1, 4245, 2391, 25, 7569\nReason: Here, the alphabets in the list are 'a' and 'Y', hence we replace them by their positions in the English alphabet '1' and '25', respectively in the input list to get '8129, 1, 4245, 2391, 25, 7569'.\n\nNow, solve this instance: ['2519', '3909', 'a', 'D', '4429', 'N', '2511', '9803', 'O', '8793', '4221', 'I', 'i', 'J', 'O', '6517', 'V', 'M', 'w', '1197', '2169', '5097', 'U', 'Q']\nStudent:" }, { "from": "gpt", "value": "2519, 3909, 1, 4, 4429, 14, 2511, 9803, 15, 8793, 4221, 9, 9, 10, 15, 6517, 22, 13, 23, 1197, 2169, 5097, 21, 17" } ]

[ { "from": "human", "value": "Given a scientific question, generate a correct answer to it.\n\n[EX Q]: Trash that gets into fresh and saltwater waterways is called what type of debris?\n[EX A]: aquatic\n\n[EX Q]: What bodily defense can be acquired in an active or passive way, and can be natural or artificial?\n[EX A]: immunity\n\n[EX Q]: Skeletal muscle cells and cardiac muscle cells share what property, which is not shared by smooth muscle cells?\n[EX A]:" }, { "from": "gpt", "value": "striations\n\n" } ]

[ { "from": "human", "value": "Instructions: The task is to generate text based off of an event. For the given event, there will be a person who does the action in the event (usually PersonX). Your task is to write that persons intent behind doing the event, i.e. why did the person do that action.\nInput: PersonX reads PersonY account\nOutput:" }, { "from": "gpt", "value": "to know more" } ]

[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nIn this task, you are given a short passage that may convey stereotype, anti-stereotype, or is unrelated. A stereotype is an over-generalized belief about a particular group of people. An anti-stereotype is an idea that goes against a common stereotype. The passage is unrelated if it does not convey a stereotype or anti-stereotype. You are expected to classify the passage into three classes: stereotype, anti-stereotype, and unrelated.\nExample: Passage: The game-winning football player is very aggressive.\nOutput: Stereotype\nIt is a stereotype because we have a standardized image that game-winning players are commonly aggresive. There is no mention of the football player's aggresive behavior.\n\nNew input case for you: Passage: The Bengali magazine was sold at the corner stand. It talked about the varying political views of the country.\nOutput:" }, { "from": "gpt", "value": "Anti-stereotype" } ]

[ { "from": "human", "value": "Detailed Instructions: Given a scientific question, generate an incorrect answer to the given question. The incorrect answer should be a plausible alternative to the correct answer. The answer should be some other item belonging to the same category as the correct answer but should be incorrect.\nSee one example below:\nProblem: What are arteries, veins, and capillaries examples of?\nSolution: tissue\nExplanation: Blood vessels include arteries, veins, and capillaries. Tissue is a combination of cells.\n\nProblem: What are the specfic types of proteins that determine your blood type called?\nSolution:" }, { "from": "gpt", "value": "Plasma" } ]

[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, you are given sentences from movie reviews. The task is to classify a sentence as \"POS\" if the sentiment of the sentence is positive or as \"NEG\" if the sentiment of the sentence is negative\n\nA technically well-made suspenser ... but its abrupt drop in IQ points as it races to the finish line proves simply too discouraging to let slide .\n" }, { "from": "gpt", "value": "NEG" } ]

[ { "from": "human", "value": "In this task, you will be presented with a context from an academic paper and a question based on the context. You have to classify the questions into \"Extractive\", \"Abstractive\", or \"Yes-no\" questions. Extractive questions can be answered by concatenating extracts taken from a context into a summary while answering abstractive questions involves paraphrasing the context using novel sentences. Yes-no question is a question whose expected answer is one of two choices, one that affirms the question and one that denies the question. Typically, the choices are either yes or no.\n\nBi-LSTM BIBREF11 is a baseline for neural models. Bi-LSTM$_{+ att. + LEX + POS}$ BIBREF10 is a multi-task learning framework for WSD, POS tagging, and LEX with self-attention mechanism, which converts WSD to a sequence learning task. GAS$_{ext}$ BIBREF12 is a variant of GAS which is a gloss-augmented variant of the memory network by extending gloss knowledge. CAN$^s$ and HCAN BIBREF13 are sentence-level and hierarchical co-attention neural network models which leverage gloss knowledge. \n Question: How does the neural network architecture accomodate an unknown amount of senses per word?" }, { "from": "gpt", "value": "Extractive" } ]

[ { "from": "human", "value": "In this task, you are given a text from tweets and a boolean question whether this tweet has positive sentiment or negative sentiment. Your task is to generate answer \"yes\" when the tweet has that particular sentiment, otherwise generate answer \"no\".\n--------\nQuestion: Tweet: the older you get the more responsibilities you have Wanna be a little child again. Question: is it a negative tweet?\n\nAnswer: yes\n\n\nQuestion: Tweet: Never mind swine flu, looks like I might be in for a dose of chicken pox Question: is it a negative tweet?\n\nAnswer: yes\n\n\nQuestion: Tweet: Finally found the relevant bits of paper! I think I need a PA! Question: is it a positive tweet?\n\nAnswer:" }, { "from": "gpt", "value": "yes\n\n\n" } ]

[ { "from": "human", "value": "Detailed Instructions: In this task, you will be given two sentences separated by \"because\". You should decide whether the first sentence can be the result of the second sentence. If you can see a possible cause and effect relationship, answer with \"plausible\", otherwise answer with \"not plausible\".\nProblem:my flight got delayed because I wasn't feeling well\nSolution:" }, { "from": "gpt", "value": "not plausible" } ]

[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nAdverse drug reactions are appreciably harmful or unpleasant reactions resulting from an intervention related to the use of medical products, which predicts hazard from future administration and warrants prevention or specific treatment, or alteration of the dosage regimen, or withdrawal of the product. Given medical case reports extracted from MEDLINE, the task is to classify whether the case report mentions the presence of any adverse drug reaction. Classify your answers into non-adverse drug event and adverse drug event.\nExample: A case is reported of a child with fatal pulmonary fibrosis following BCNU therapy.\nOutput: adverse drug event\nHere, the child is facing some trouble after undergoing a particular therapy, thereby causing an adverse effect of the therapy.\n\nNew input case for you: Acute acoustic nerve palsy associated with vincristine therapy.\nOutput:" }, { "from": "gpt", "value": "adverse drug event" } ]

[ { "from": "human", "value": "Detailed Instructions: Classify the given tweet into the three categories: (1) 'Hate Speech', (2) 'Offensive' and (3) 'Neither'. 'Hate Speech' is kind of a threating statement or sometimes include call for violence while 'offensive' statement just offensds someone. 'Neither' is when it doesn't fall into Hate Speech or Offensive category.\nProblem:1st game of Fall 7s.. finna kill some hoes\nSolution:" }, { "from": "gpt", "value": "Offensive" } ]

[ { "from": "human", "value": "Detailed Instructions: In this task, you are given two facts, and a multiple-choice question. Based on the given facts, answer the question with index of the correct option (e.g, \"A\").\nQ: Fact1: Mammals generate heat mainly by keeping their metabolic rate high., Fact2: And resting metabolic rate is a big contributor to calories burning., Question: Mammals generate heat mainly by what? (A) hugging mammals (B) calorie counting (C) with their fur (D) energy of moving objects (E) burning calories (F) sweating (G) selling fur coats (H) flow of electrons\nA:" }, { "from": "gpt", "value": "E" } ]

[ { "from": "human", "value": "Given a premise, an initial context, an original ending, and a new ending, the task is to generate the counterfactual context that is aligned with the new ending. Each instance consists of a five-sentence story. The premise is the first sentence of a story, and the second sentence, which is the initial context, provides more information about the story's context. The original ending is the last three sentences of the story. Also, you are given a new ending that can provide the new story with the same premise. You should write a counterfactual context to explain the small differences between the original and new endings. More specifically, a story context contains the general plot of the story. And a counterfactual context is a slight modification to the initial context. To sum up, you should write the second sentence of a story based on the premise(first sentence) and the new ending(last three sentences) of the story.\n\nPremise: I took my wedding ring off to clean it. \n Initial Context: I accidentally dropped it on the ground. \n Original Ending: It rolled away into a corner. I searched and found the ring. I put it back on my finger. \n New ending: It rolled away out of reach. I searched with chopsticks and found the ring. I put it back on my finger. \nI accidentally dropped it into the disposal.\n\nPremise: When I came home from school, I dressed up for a party. \n Initial Context: Before I left the house, my mom called me. \n Original Ending: She asked if I can pay for dinner tonight. Although I barely had money, I decided to buy Chinese Takeout. I spent all of my money and decided to miss the party. \n New ending: She asked if I can pay for dinner tonight. Although I barely had money, I decided to buy Chinese Takeout. I spent all of my money but had a great meal with my mom after the party. \nJust as I left the party to come home, my mom called me.\n\nPremise: Marcus decides that he wants to play a sport this Spring. \n Initial Context: He has always been a great runner. \n Original Ending: He decides to try out for the track team. Marcus practices very hard until tryouts begin. Marcus succeeds in tryouts and makes the team! \n New ending: He decides to try out for the swim team. Marcus practices very hard until tryouts begin Marcus succeeds in tryouts and makes the team \n" }, { "from": "gpt", "value": "He has always been a great swimmer.\n\n" } ]

[ { "from": "human", "value": "Definition: Given a story, answer the question about the story. The question is the last sentence in the input. The story has 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.\nInput: Mia entered the staircase. Emily entered the staircase. The lettuce is in the blue_box. Emily exited the staircase. Phone rang. Mia moved the lettuce to the red_bottle. Where does Mia think that Emily searches for the lettuce?\nOutput:" }, { "from": "gpt", "value": "blue_box" } ]

[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task you will be given a string that only contains single digit numbers spelled out. The input string will not contain spaces between the different numbers. Your task is to return the number that the string spells out. The string will spell out each digit of the number for example '1726' will be 'oneseventwosix' instead of 'one thousand seven hundred six'.\n\neightzerofiveeightthreetwofourtwoone\n" }, { "from": "gpt", "value": "805832421" } ]

[ { "from": "human", "value": "Detailed Instructions: In this task, you're given the middle and ending of a three-part story. Your job is to complete the short story by writing a probable beginning of the story. Generated sentences must be short, have fewer than 10 words, and be simple as if narrating to a child. Avoid using any irrelevant extra information when creating the beginning, and use names (e.g. Jack, Barbara,...) instead of pronouns (e.g. he / she) wherever possible.\nSee one example below:\nProblem: Middle: Helen planned to drive to Canada but it started snowing heavily. Ending: Helen stayed home instead and planned to go another day.\nSolution: Helen lived in America.\nExplanation: Mention of the destination country name and driving implies that Helen is from a nearby foreign country.\n\nProblem: Middle: Ellen accidentally let go of the balloon. Ending: Ellen decided not to cry and enjoyed watching it till it disappeared.\nSolution:" }, { "from": "gpt", "value": "Ellen received a beautiful, helium-filled balloon for her birthday." } ]

[ { "from": "human", "value": "Instructions: Given a sentence in German, generate a new German sentence by performing small changes on the sentence. Here, make sure that the changes are semantically related and syntactically similar to the input. And the generated sentence should have high commonsense plausibility, that is to have reasonable probability of it being true.\nInput: Ihre Heimatstadt ist die Stadt, in der Sie geboren wurden.\nOutput:" }, { "from": "gpt", "value": "Ihre Heimatstadt ist der Pub, in den Sie eingeladen wurden." } ]

[ { "from": "human", "value": "In this task, you are given a review of a movie and a boolean question whether this review has positive sentiment or negative sentiment. Your task is to generate answer \"yes\" when the tweet has that particular sentiment, otherwise generate answer \"no\".\n\n[EX Q]: Review: My spouse & I found this movie to be very schlocky. It started out good, but quickly got unbelievable & ridiculous. Most of the acting was poor, with the exception of the little girl, Abbie, who really was terrific. In addition, the dialog was predictable & lame - especially Gideon, the Angel's. Also, without giving away anything, when one of the characters has a tragedy, she almost appears nonchalant. At first we thought it was 'shock', but then we realized that it was just a terrible script. We love almost all of the Hallmark movies & their heart-warming stories, but this movie doesn't rise to the occasion of being one. There are so many great ones - don't waste your time with this horrible movie. Question: is it a positive review?\n[EX A]: no\n\n[EX Q]: Review: I saw this film with a special screening of the work of Owen Alik Shahadah. It is so interesting where did this guy come from. Now he is probably the key independent African filmmaker in the world. And I am not talking about black filmmakers I am talking about filmmakers who are rooted in culture. The idea if anything testifies to the diversity and range of African themes, with his film 500 Years Later it is a African issue. But the Idea doesn't fit that mold. Showing the artistic diversity. The film is an all African cast but the topic is a human topic which most of us could relate to. I just love the mild comedy in it. And the Kora of Tunde Jegede is just amazing, it is really a art-house gem. Question: is it a positive review?\n[EX A]: yes\n\n[EX Q]: Review: I thought this was a very good movie. It would have been nice to have seen a little more into the movie about the 2 sisters knowing about each liking the same boy before he was killed off. I'm sure if the movie had been done this way there would have been a very different ending, that's why this made this move such a good movie. It shows that no matter what happens in your life with your siblings that you can always get thru it and that if it's 2 sisters dealing with a boy, (the same boy) that working thru the pain and hurt makes things to seem better and easier to work out between the 2 of them. It's nice to see love stories that have a terrible thing to happen in someone's life that you can still get thru it become even closer after its over. I really enjoyed watching this movie, and I still do now when it comes on. I seem to find myself watching it every time it comes on. It would have been nice if there would have been a part 2 for this movie, maybe having the older sister to come up and have his baby, this would really have made a great finish to the story since he died, this way it would keep him alive even though he's dead. Question: is it a positive review?\n[EX A]:" }, { "from": "gpt", "value": "yes\n\n" } ]

[ { "from": "human", "value": "Given the task definition and input, reply with output. You will be given a summary of a story. You need to create a question that can be answered from the story. You can create a question about characters, events, facts and beliefs, etc. Your question should be specific, try not to use pronouns instead of full names. As the stories are sometimes movie plots, they will contain actor names in parentheses. You should not use those names. Only use character names. Try to ask a question about all parts of the plot, not just the beginning.\n\n (From Conan The Warrior, ISBN 0-441-11465-2)\nThe foreword to the story tells of his travels to Punt with Muriela, refers to a scam perpetrated against worshippers of an ivory goddess and then on to Zembabwei, where he joins a trading caravan on its way to Shem. Around 40 now, Conan visits his homeland and finds his old friends are fathers. Bored, Conan sets off for the Bossonian Marches and becomes a Scout at Fort Tuscelan on the Black River. Naturally, there is a war going on...\nA young settler named Balthus encounters Conan in the forests slaying a forest devil. Accompanying the young man back to the Fort, Conan finds the body of a merchant ensorcelled by a Pictish wizard named Zogar Sag and slain by a swamp demon.\nThe Fort Tuscelan Commander, Valannus, is a desperate man and asks Conan to slay Zogar Sag before he raises the Picts against the whole borderlands. Taking a hand picked team of scouts and Balthus, Conan sets off stealthily in canoes. Balthus is captured and most of Conan's men slaughtered in an ambush.\nBalthus and one of the Scouts are tied to stakes and the scout is sacrificed by Zogar Sag to one of his jungle creatures. Before Balthus can meet a similar fate, Conan sets the Pictish village on fire and the two flee into the woods. Conan tells Balthus of the cult of Jhebbal Sag, now forgotten by most. Once all living things worshipped him when men and beasts spoke the same language. Over time men and most beasts forgot his worship. Zogar Sag has not, however, and can control those few animals and creatures who also remember. And they are on Conan's trail now.\nConan is able to neutralize them using a symbol he once noticed, and the pair hurry to return to the Fort to warn them of the impending Pictish assault, but they are too late. The Picts already are all around the fort, and furious fighting is going on. The number of Picts ensures that eventually the fort will be overwhelmed and the defenders slaughtered. The only thing left to do is warn the settlers to flee while the Picts are busy with the fort - otherwise they will be slaughtered, too.\nConan and Balthus go to warn the settlers that the Picts have crossed the river and are raiding. They are joined by Slasher, a feral dog formerly owned by a settler who had been slain by the Picts. Balthus is sent on to warn settlers of the coming Pict raid, and Conan parts from him to warn a group of settler who had gone to gather salt. Balthus warns women and children to leave their huts and flee. When a band of Picts arrives, who move quicker and might overtake the women, Balthus stays behind to cover their escape. Accompanied by Slasher he makes a stand against the coming Pict raiders, first shooting arrows from concealment and then in a furious face to face battle. The man and dog's sacrifice delays the Picts and gives the settlers time to reach safety. Conan manages to warn the salt-gathering party in time, but finds he has been marked for death by the gods of darkness for misusing the symbol of Jhebbal Sag. In the end Conan triumphs, but the fort is lost, and so is the entire province.\nThe story ends in a tavern. A survivor tells Conan about the courageous act of Balthus and Slasher, and how their final stand had delayed the Picts just barely long enough for the settlers to reach safety. Upon hearing of the fight, Conan vowed to take the heads of ten Picts to pay for Balthus' sacrifice, along with seven heads for the dog, who was \"a better warrior than many a man.\"\n" }, { "from": "gpt", "value": "Who goes to warn the salt gatherers?" } ]

[ { "from": "human", "value": "Given the task definition, example input & output, solve the new input case.\nIn this task you will be given a list, of lists, of numbers. Each list is presented with brackets and comma-separated values. For example, a list of numbers is [1,2,3] and a list of two lists of numbers is [[1,2],[3,4,6]]. You should sum up the values at every position of every inner list and put it as an element of your answer, that is, you should sum the first members of each inner list together and put it as the first element of the list, then sum the second members of each inner list together and put it as the second element of your list, etc. The output should be a list of numbers with the same length as the longest inner list.\nExample: [[6, 3, 8], [7, -5]]\nOutput: [13, -2, 8]\nWe start by summing up the first elements of all the lists: 6 + 7 = 13, so the first element of the output is 13. For the second element of the output, we sum up the second elements of all the lists: 3 + (-5) = -2. One of the lists doesn't have a third element, so the third element of the answer is: 8 + 0 = 8.\n\nNew input case for you: [[87, 35, 35, -81, -26, 7, -32, -25, 71], [-88, -20, 38, 34]]\nOutput:" }, { "from": "gpt", "value": "[-1, 15, 73, -47, -26, 7, -32, -25, 71]" } ]

[ { "from": "human", "value": "Given the task definition and input, reply with output. 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 find all elements of A from the ith element to the jth element, reverse the order in which they occur, and then concatenate them to output the resultant string. 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. Perform the operations in order, i.e., do not concatenate the elements and then reverse the string.\n\n8, 16, ['W', 'v', 'S', '8001', 'r', 'S', 'E', 'b', '1255', 's', 'Y', 'R', '589', '6483', 'C', 'H', '7169', '7693', '2957', '6045', 'X']\n" }, { "from": "gpt", "value": "HC6483589RYs1255b" } ]

[ { "from": "human", "value": "In this task you are given a list of numbers and you need to find the average of each two consecutive values. The average of two numbers a and b is calculated as: (a + b) /2. The output should be a list of the averages of each two consecutive values. A list is presented with two brackets and comma-separated values, like: [1,2,3].\n\n[Q]: [-38, -61, -23, -94, -64, 18, -26, -96, -92, 96, -34, -80, -13, 45, -83]\n[A]: [-49.5, -42.0, -58.5, -79.0, -23.0, -4.0, -61.0, -94.0, 2.0, 31.0, -57.0, -46.5, 16.0, -19.0]\n\n\n[Q]: [78, 3, 3, 50, 80, -76, -73, -20, -71, -29, -47, 4]\n[A]: [40.5, 3.0, 26.5, 65.0, 2.0, -74.5, -46.5, -45.5, -50.0, -38.0, -21.5]\n\n\n[Q]: [-96, -42, -34, 57, -47, -54, 40, 97, 16, -76, -31, -24, 25, 81, -7]\n[A]:" }, { "from": "gpt", "value": "[-69.0, -38.0, 11.5, 5.0, -50.5, -7.0, 68.5, 56.5, -30.0, -53.5, -27.5, 0.5, 53.0, 37.0]\n\n\n" } ]

[ { "from": "human", "value": "You are provided with an \"Event\", \"Intent\" and \"XEmotion\" (PersonX's reactions for the given \"Event\"). Indicate PersonY's reaction (person feels) at the end of this event. Provide one reaction for PersonY. If there's nothing that can be implied, respond as None\n\nExample input: Event: PersonX not does PersonY any favours. Intent: 1) to inflict pain. XEmotion: 1) has no feelings\nExample output: horrible\nExample explanation: Based on the given input PersonX is trying to inflict pain on PersonY as it has no feelings. PersonY being a third person might show an emotion of feeling horrible which is provided in the output\nQ: Event:PersonX gives the dog away. Intent: 1) to talk to me.. XEmotion: 1) good.\nA:" }, { "from": "gpt", "value": "glad" } ]

[ { "from": "human", "value": "In this task, you're given the beginning and the middle of a three-part story. Your job is to complete the short story by writing a probable ending. Generated sentences must be short, have fewer than 10 words, and be simple as if narrating to a child. Avoid using any irrelevant extra information when creating the ending, and use names instead of pronouns (e.g. he / she) wherever possible.\n\nLet me give you an example: Beginning: Helen lived in the state of Washington. Middle: Helen planned to drive to Canada but it started snowing heavily.\nThe answer to this example can be: Helen stayed home instead and planned to go another day.\nHere is why: Generally, people prefer not to drive in bad weather.\n\nOK. solve this:\nBeginning: Today I drove to the library in order to meet up with my group. Middle: I read a book about marrital abuse.\nAnswer:" }, { "from": "gpt", "value": "I spoke about domestic violence." } ]

[ { "from": "human", "value": "Given a command in a limited form of natural language, provide the correct sequence of actions that executes the command to thus navigate an agent in its environment. A command can be broken down into many different actions. Actions are uppercase and are individual steps that serve as the building blocks for a command. For commands, 'left' and 'right' are used to denote the direction of an action. The word 'opposite' turns the agent backward in the specified direction. The word 'around' makes the agent execute an action while turning around in the specified direction. The word 'and' means to execute the next scope of the command following the previous scope of the command. The word 'after' signifies to execute the previous scope of the command following the next scope of the command. The words 'twice' and 'thrice' trigger repetition of a command that they scope over two times or three times, respectively. There are only six actions: 'I_LOOK', 'I_WALK', 'I_RUN', 'I_JUMP', 'I_TURN_LEFT', and 'I_TURN_RIGHT'. These actions respectively align with the commands 'look', 'walk', 'run', 'jump', 'turn left', and 'turn right'. Actions and commands do not have quotations in the input and output.\n\nQ: run right and look right thrice\n\nA: I_TURN_RIGHT I_RUN I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK I_TURN_RIGHT I_LOOK\n****\nQ: walk right twice and turn around right twice\n\nA: I_TURN_RIGHT I_WALK I_TURN_RIGHT I_WALK I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT I_TURN_RIGHT\n****\nQ: jump left twice and jump around right\n\nA:" }, { "from": "gpt", "value": "I_TURN_LEFT I_JUMP I_TURN_LEFT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP I_TURN_RIGHT I_JUMP\n****\n" } ]

[ { "from": "human", "value": "In this task, you are given an input list A. You need to find all the elements of the list that are numbers in the same order as they appear in the list A.\n\n[EX Q]: ['9061', 'I', '1665', 'k', '2661', 'O', 'r', '1149', '4231', 'k', '6527', '725', '6545', 'V', 'w', 'j', 'A', 'h', '9737', 'M', 'u', 'L', '7367', '4761', '4763', '7565', '1185', '3097', '4001']\n[EX A]: 9061, 1665, 2661, 1149, 4231, 6527, 725, 6545, 9737, 7367, 4761, 4763, 7565, 1185, 3097, 4001\n\n[EX Q]: ['s', '131', 's', '7453', 'H', 'J', 'f', '2047']\n[EX A]: 131, 7453, 2047\n\n[EX Q]: ['81', 'u', 'N', '8727', 'J', '3981', 'F', 'z', '7313', 'b', '1501', '2769', '2089', '8493', '4835', 'r', 'n', '2177', '4725', '5163', 'z']\n[EX A]:" }, { "from": "gpt", "value": "81, 8727, 3981, 7313, 1501, 2769, 2089, 8493, 4835, 2177, 4725, 5163\n\n" } ]

[ { "from": "human", "value": "Teacher: In this task you are given a sentence. You must judge whether there exist two consecutive words within the sentence with flipped orders, that is, whether the sentence will make sense and be correct if the order of two consecutive words changes. Label the instances as \"Inversion\" or \"Original\" based on your judgment.\nTeacher: Now, understand the problem? If you are still confused, see the following example:\nHe poured out his to heart God, and after a few minutes the need left him, for a while anyway.\nSolution: Inversion\nReason: \"heart\" and \"to\" have been inverted.\n\nNow, solve this instance: Owen smiled, his violet eyes soft with old memories.\nStudent:" }, { "from": "gpt", "value": "Original" } ]

[ { "from": "human", "value": "Given the task definition and input, reply with output. In this task, you are given a public comment from online platforms. You are expected to classify the comment into two classes: obscene and non-obscene. A comment is obscene if it is considered offensive to the public sense of decency, for example because it too obviously relates to sex or contains language regarded as taboo in polite usage.\n\nComment: While I highly doubt Mr Poplak needs me to defend his writing, I will say that 'fuck' is merely a word - a real word that can be found in the dictionary (right between 'fuchsia' and 'fuddle'), so why should there be a problem with using it for shock and emphasis? And honestly, if someone is going to be that badly affected by reading those four little letters, they're better off not reading Poplak's articles anyway, as he tends to deal with topics that are far heavier than one silly little swear word.\n\nOr to put it another way, as Stephen Fry said: \"If my words offend you, well so fucking what?\"\n" }, { "from": "gpt", "value": "Obscene" } ]

[ { "from": "human", "value": "instruction:\nIn 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.\nquestion:\n2, 5, ['9153', 'S', '605', '2951', 'I', 'o', '4995', '2895']\nanswer:\n3556\n\n\nquestion:\n5, 18, ['T', '7117', '7067', 't', '7083', '5711', '6735', 's', '4879', '2553', 'a', 'z', 'Q', '4759', '6243', 'k', 'V', '7803', '2489', 'j', '9449', '8017', '9739', 'F', '1557']\nanswer:\n45766\n\n\nquestion:\n3, 7, ['1687', '1929', '3189', '3277', 'L', 'b', 'x', '3181', 'C', 'w', 'A', 't', 'I', '3421']\nanswer:\n" }, { "from": "gpt", "value": "6466\n\n\n" } ]

[ { "from": "human", "value": "Teacher:In this task, you are given an input stream, and your task is to produce a grammatically correct version of the input sentence. The input to this task is a stream of words, possibly from captions generated by a speech-to-text engine, and the output is a grammatically correct version of the input stream. Stream words are in [] and have been separated with a comma. The sentence can contain words that have case, punctuation, stem-based, intra-word, and digit punctuation errors that need to be corrected. For example, the text should be uppercased/lowercased as per necessity (like the beginning of a sentence, proper nouns, etc.), and digits need to be normalized (6 as six and so on). Note that you don't need to normalize the years. You don't need to fully edit the sentences, if end of the input stream contains sentence fragments, keep them as is.\nTeacher: Now, understand the problem? Solve this instance: ['so', 'autism', 'spectrum', 'disorder', 'is', 'a', 'really', 'broad', 'social', 'disorder', 'that', 'affects', 'the', 'way', 'that', 'someone', 'communicates', 'and', 'interacts', 'with', 'other', 'people', 'and', 'the', 'reason', 'that', 'I', 'say', \"it's\", 'a', 'really', 'broad', 'disorder', 'the', 'reason', 'we', 'call', 'it', 'a', 'spectrum', 'disorder', 'is', 'because', 'each', 'person', 'with', 'autism', 'spectrum', 'disorder', 'is', 'affected', 'a', 'little', 'differently', 'no', 'two', 'people', 'with', 'autism', 'structure', 'disorder', 'are', 'exactly', 'the', 'same', 'so', 'we', 'say', 'that', 'different', 'people', 'with', 'autism', 'spectrum', 'disorder', 'follow', 'along', 'a', 'spectrum', 'and', 'along', 'this', 'spectrum', 'there', 'are', 'different', 'symptoms', 'different', 'challenges', 'and', 'different', 'abilities', 'that', 'vary', 'a', 'lot', 'in', 'severity', 'and', 'vary']\nStudent:" }, { "from": "gpt", "value": "['so', 'autism', 'spectrum', 'disorder', 'is', 'a', 'really', 'broad', 'social', 'disorder', 'that', 'affects', 'the', 'way', 'that', 'someone', 'communicates', 'and', 'interacts', 'with', 'other', 'people.', 'And', 'the', 'reason', 'that', 'I', 'say', \"it's\", 'a', 'really', 'broad', 'disorder,', 'the', 'reason', 'we', 'call', 'it', 'a', '\"spectrum', 'disorder\"', 'is', 'because', 'each', 'person', 'with', 'autism', 'spectrum', 'disorder', 'is', 'affected', 'a', 'little', 'differently.', 'No', 'two', 'people', 'with', 'autism', 'spectrum', 'disorder', 'are', 'exactly', 'the', 'same.', 'So', 'we', 'say', 'that', 'different', 'people', 'with', 'autism', 'spectrum', 'disorder', 'fall', 'along', 'a', 'spectrum,', 'and', 'along', 'this', 'spectrum', 'there', 'are', 'different', 'symptoms,', 'different', 'challenges', 'and', 'different', 'abilities', 'that', 'vary', 'a', 'lot', 'in', 'severity', 'and', 'vary']" } ]

[ { "from": "human", "value": "Turn the given fact into a question by a simple rearrangement of words. This typically involves replacing some part of the given fact with a WH word. For example, replacing the subject of the provided fact with the word \"what\" can form a valid question. Don't be creative! You just need to rearrange the words to turn the fact into a question - easy! Don't just randomly remove a word from the given fact to form a question. Remember that your question must evaluate scientific understanding. Pick a word or a phrase in the given fact to be the correct answer, then make the rest of the question. You can also form a question without any WH words. For example, \"A radio converts electricity into?\"\nOne example is below.\nQ: Fact: pesticides can harm animals.\nA: What can harm animals?\nRationale: It's a good question because it is formed by simply replacing the word \"pesticides\" with \"what\".\nQ: Fact: a firecracker converts chemical energy into vibrating waves.\nA:" }, { "from": "gpt", "value": "a firecracker converts chemical energy into what?" } ]

[ { "from": "human", "value": "Instructions: Given the sentence, generate \"yes, and\" response. \"Yes, and\" is a rule-of-thumb in improvisational comedy that suggests that a participant in a dialogue should accept what another participant has stated (\"Yes\") and then expand on that line of thought or context (\"and...\"). 1 In short, a \"Yes, and\" is a dialogue exchange in which a speaker responds by adding new information on top of the information/setting that was constructed by another speaker. Note that a \"Yes, and\" does not require someone explicitly saying 'yes, and...' as part of a dialogue exchange, although it could be the case if it agrees with the description above. There are many ways in which a response could implicitly/explicitly agree to the prompt without specifically saying 'yes, and...'. \nInput: Mr. President, my friend it outside somewhere. You probably just missed her because she's very short and hunched.\nOutput:" }, { "from": "gpt", "value": "Oh, she's hunched? She's carrying a lot of stuff?" } ]

[ { "from": "human", "value": "TASK DEFINITION: In this task you are given a medical question pair hand-generated. Your task is to classify a given post into two categories 1) 'Similar' if the given two questions have a same connotation 2) 'Dissimilar' if the given two questions have a different connotation or meaning.\nPROBLEM: Sentence1: I've got a stabbing pain in my groin in scrotum, what would cause this? \n Sentence2: What does sharp excrutiating pain in the groin and scrotum mean? What can cause this?\n\nSOLUTION: Similar\n\nPROBLEM: Sentence1: What is the life expectancy for someone with mixed connective tissue disease? \n Sentence2: How is mixed connective tissue disease diagnosed? What are some complications of this disease that may affect the life expectancy of such patients?\n\nSOLUTION: Dissimilar\n\nPROBLEM: Sentence1: How do you safely remove a swimmer with a possible head injury from the water? \n Sentence2: How do you safely remove a swimmer out of water who has a head injury?\n\nSOLUTION:" }, { "from": "gpt", "value": "Similar\n\n" } ]

[ { "from": "human", "value": "In this task the focus is on physical knowledge about the world. Given the provided goal task in the input, describe a process that would lead to the asked outcome. This process often involves physical motions with objects, such as moving them, arranging them in a certain way, mixing them, shaking them, etc. \n--------\nQuestion: How should you cut tomatoes in order to put into salsa?\n\nAnswer: Get a tomato and place it on a cutting board. Using a kitchen knife, cut the tomato in half crosswise. Squeeze out and discard the bulk of the seeds and juice. Chop the tomato halves into cubes and then put the cubes in a bowl.\n\n\nQuestion: To create cold air in a DIY air conditioner made from a fan enclosed in a Styrofoam box.\n\nAnswer: Put a bottle of frozen water in the box with the fan.\n\n\nQuestion: how to DIY a grease trap for a grill\n\nAnswer:" }, { "from": "gpt", "value": "place a disposable pie tin or a homemade one made from heavy-duty foil, on top of an unlit burner under the grates to catch the drippings\n\n\n" } ]

[ { "from": "human", "value": "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.\n\nQ: Charlotte entered the dining_room. Liam entered the dining_room. The banana is in the red_bottle. Liam exited the dining_room. Charlotte moved the banana to the red_drawer. Liam entered the front_yard. Evelyn entered the front_yard. The grapefruit is in the blue_pantry. Evelyn exited the front_yard. Liam moved the grapefruit to the blue_cupboard. Charlotte entered the back_yard. Evelyn entered the back_yard. The pineapple is in the blue_treasure_chest. Evelyn exited the back_yard. Charlotte moved the pineapple to the green_treasure_chest. Charlotte entered the closet. Ethan entered the closet. The potato is in the red_box. Ethan exited the closet. Charlotte moved the potato to the red_treasure_chest. Where was the potato at the beginning?\n\nA: red_box\n****\nQ: Amelia entered the front_yard. Emily entered the front_yard. The persimmon is in the red_treasure_chest. Amelia moved the persimmon to the red_envelope. Emily entered the den. Amelia entered the den. The spinach is in the blue_cupboard. Emily moved the spinach to the blue_treasure_chest. Amelia entered the basement. William entered the basement. The pear is in the green_cupboard. Amelia moved the pear to the green_bucket. William entered the front_yard. Amelia entered the front_yard. The banana is in the red_envelope. William moved the banana to the red_treasure_chest. Where was the banana at the beginning?\n\nA: red_envelope\n****\nQ: Aria entered the master_bedroom. Olivia entered the master_bedroom. The pumpkin is in the green_suitcase. Olivia exited the master_bedroom. Aria moved the pumpkin to the blue_bathtub. Aria exited the master_bedroom. Olivia entered the master_bedroom. Where does Aria think that Olivia searches for the pumpkin? Owen entered the attic. Olivia entered the attic. The peach is in the red_bucket. Owen moved the peach to the green_crate. Where was the peach at the beginning? Olivia entered the hallway. Owen entered the hallway. The grapes is in the red_crate. Owen exited the hallway. Olivia moved the grapes to the red_treasure_chest. Olivia exited the hallway. Owen entered the hallway. Where is the grapes really? Logan entered the attic. Olivia entered the attic. The corn is in the green_crate. Logan moved the corn to the red_bucket. Where was the corn at the beginning? Olivia entered the dining_room. Logan entered the dining_room. The apple is in the red_box. Logan exited the dining_room. Olivia moved the apple to the green_box. Olivia exited the dining_room. Logan entered the dining_room. Where was the apple at the beginning?\n\nA:" }, { "from": "gpt", "value": "red_box\n****\n" } ]

[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you are given two simple actions (associated with \"A\", \"B\"). You must identify which action is considered less ethical. Do not generate anything else apart from one of the following characters: 'A', 'B'.\n\n(A) responding late in the group chat\n(B) wanting to split up with my so because my physical attraction to her has diminished, and being honest if she asks why? this woman is otherwise perfect (career, stable, caring, etc.) I'm a solid 8/10 overall, I don't think my standards are too high, I know looks fade, etc\nOutput:" }, { "from": "gpt", "value": "B" } ]

[ { "from": "human", "value": "Teacher:In this task you will be given a list of numbers. A list is shown by two brackets and comma-separated numbers inside, like: [1,2,3]. You should remove all of the even numbers from the list. If every number in the input list is even an empty list should be returned. Zero should be counted as an even number.\nTeacher: Now, understand the problem? Solve this instance: [35, 71, 159, 56, 52, 166, 39, 57]\nStudent:" }, { "from": "gpt", "value": "[35, 71, 159, 39, 57]" } ]

[ { "from": "human", "value": "Detailed Instructions: In this task you will be given a list of dictionaries. A dictionary is a set of key-value pairs, where each key is unique and has a value associated with that key. You should sort the list of dictionaries from smallest to largest by their 'first' key. If there is two dictionaries with the same 'first' value then sort them by their 'second' key. Negative numbers should come before positive numbers.\nProblem:[{'first': -10, 'second': 35}, {'first': -26, 'second': -14}, {'first': -17, 'second': -63}, {'first': -61, 'second': 5}]\nSolution:" }, { "from": "gpt", "value": "[{'first': -61, 'second': 5}, {'first': -26, 'second': -14}, {'first': -17, 'second': -63}, {'first': -10, 'second': 35}]" } ]

[ { "from": "human", "value": "Instructions: Based on the given question and tppic, give an answer. The answer is available on on the internet. The questions are mostly centered around a single named entity.\nInput: concept: Alani Vasquez question: where does lala anthony live?\nOutput:" }, { "from": "gpt", "value": "['Brooklyn']" } ]

[ { "from": "human", "value": "In this task, you are given a text from a social media post. Your task is to classify the given post into two categories: 1) yes if the given post is intentionally offensive, 2) no, otherwise. Also, generate label 'no' for offensive statements that appear to be unintentional, or non-offensive statements that are underhandedly offensive. Warning: the examples and instances may contain offensive language.\nOne example: Living alone rocks. Being sick and living alone sucks. Will bake someone many a baked good for some NyQuil / DayQuil rn.\nSolution is here: No\nExplanation: This is a good example of a post that is not intended to offend. There is no sign of intention to offend and no offensive language is used. This is simply a post about the pitiful state of the poster.\n\nNow, solve this: \" we dont trust these niggas all these bitches \"\nSolution:" }, { "from": "gpt", "value": "No" } ]

[ { "from": "human", "value": "Detailed Instructions: You will be given a context and a verb separated with a newline character. You have to identify if the given verb implies an opinion, an intention, a wish or not. Please note that a verb refers to an intention only if it refers to an event planned to happen in the future and is not conditional (or part of a condition). The output should be: 'Yes' if the verb refers to an opinion, an intention, or a wish; and 'No' otherwise.\nQ: ( 0735 GMT ) Friday, toppling a crowded building toward the embassy and a street packed with cars, trucks and buses. At least 75 people were killed and 1,643 wounded there, Red Cross and ambulance officials (said). \n Verb: said\nA:" }, { "from": "gpt", "value": "No" } ]

[ { "from": "human", "value": "Detailed Instructions: This task is about using the specified sentence and converting the sentence to Resource Description Framework (RDF) triplets of the form (subject, predicate object). The RDF triplets generated must be such that the triplets accurately capture the structure and semantics of the input sentence. The input is a sentence and the output is a list of triplets of the form [subject, predicate, object] that capture the relationships present in the sentence. When a sentence has more than 1 RDF triplet possible, the output must contain all of them.\nQ: Earl Watson had the high assists during a game at the Toyota Center with a crowd of 18,370.\nA:" }, { "from": "gpt", "value": "[['79', 'HIGH_ASSISTS', 'earl watson (8)'], ['79', 'ATTENDANCE', 'toyota center 18,370']]" } ]

[ { "from": "human", "value": "You will be given a definition of a task first, then some input of the task.\nIn this task, you're given a context passage. Your job is to generate relevant questions that can be answered by directly referring to the passage.\n\nMy friend was having relationship troubles and Tracy knew she could help.\nOutput:" }, { "from": "gpt", "value": "What will happen to Tracy?" } ]

[ { "from": "human", "value": "Detailed Instructions: In this task, you're given the title of a story consisting of five sentences, numbered 1 through 5. Your job is to determine which two sentences need to be swapped sentences in order to make a story that makes complete sense and is befittingly titled. Indicate your answer using the numbers of the two sentences in order, such as '34' or '25'. The first digit refers to the sentence which should come first in the story.\nSee one example below:\nProblem: Title: Marcus Buys Khakis. Sentence 1: Marcus needed clothing for a business casual event. Sentence 2: The pair he bought fit him perfectly. Sentence 3: He decided to buy a pair of khakis. Sentence 4: All of his clothes were either too formal or too casual. Sentence 5: Marcus was happy to have the right clothes for the event.\nSolution: 24\nExplanation: Marcus's reasons for buying khakis is established, followed by his purchase of them and reaction.\n\nProblem: Title: Crusty Food. Sentence 1: Ursula took out several ingredients to prepare eggs. Sentence 2: She cracked two eggs open and placed them in a pan. Sentence 3: They started to sizzle. Sentence 4: However, she wasn't aware when they burned to a crisp. Sentence 5: Ursula left the eggs for several minutes.\nSolution:" }, { "from": "gpt", "value": "54" } ]