messages listlengths 1 1 | ground_truth stringlengths 285 19k | dataset stringclasses 1
value | constraint_type stringclasses 24
values | constraint stringclasses 24
values |
|---|---|---|---|---|
[
{
"content": "Student: Premise: \"Girl with short hair playing guitar.\"\nHypothesis: \"Girl playing a guitar.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- it is not possible to tell\n- no.\nTeacher: Let's think:\n From Answer with one of the following options: yes/no/maybe",
"role": "u... | {"func_name": "validate_choice", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": "yes/no/maybe", "section_splitter": null, "original_prompt": null} | ifeval | Choose | From Answer with one of the following options: {options} |
[
{
"content": "Answer with at most 35 words \"Kakkakuyil\", given a list of categories: company, educational institution, artist, athlete, office holder, mean of transportation, building, natural place, village, animal, plant, album, film or written work, what category does the title belong to?\nA:",
"role":... | {"func_name": "validate_word_constraint", "N": 35, "quantifier": "at most", "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Words | Answer with at least / around / at most {N} words |
[
{
"content": "Highlight at least 8 sections in your answer with markdown, i.e. *highlighted section* If I tell you that Igneous rocks are formed when magma solidifies, and ask you the question \"gneous rocks are formed when magma\", is the correct answer \"barrel-shaped\"?\nOPTIONS:\n- Yes\n- No\nNo\n--\nIf I t... | {"func_name": "validate_highlighted_sections", "N": 8, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Minimum Number Highlighted Section | Highlight at least {N} sections in your answer with markdown, i.e. *highlighted section* |
[
{
"content": "In your response, the letter d should appear 4 times. Suggest a 3 day itinerary for Joshua Tree NP. I will be staying in Yucca Valley. I want to do one medium and one easy hike. I want to attend a yoga class. I want to visit popular coffee shops and restaurants. I will need to charge my Tesla Y wh... | {"func_name": "verify_letter_frequency", "N": 4, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": "d", "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Letter Frequency | In your response, the letter {letter} should appear {N} times. |
[
{
"content": "I have a .patch file for a git repo. How can I apply that? Entire output should be wrapped in JSON format.",
"role": "user"
}
] | {"func_name": "validate_json_format", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | JSON Format | Entire output should be wrapped in JSON format. |
[
{
"content": "Answer with at most 22 words To answer the question, consider the following: Feist performed an alternate version of \"1234\" on Sesame Street during its 39th season (2008), teaching children to count to the number four.is the reasoning for what question and answer pair?",
"role": "user"
}
] | {"func_name": "validate_word_constraint", "N": 22, "quantifier": "at most", "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Words | Answer with at least / around / at most {N} words |
[
{
"content": "How can I calculate the mathematical constant e in Ruby code? I need to use it in my program to perform exponential calculations. \nIn Ruby, you can calculate e using the following code:\ne = 1\nfactorial = 1\nn = 10 # or any other number of terms in the series\n(1..n).each do |i|\n factorial *= ... | {"func_name": "verify_keywords", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": ["stumpiness", "rosoli"], "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Include Keywords | Include keywords {keyword1}, {keyword2} in your response. |
[
{
"content": "Detailed logic: Manipulation means influencing someone in right or wrong way. One needs to influence people in order to get work done from them. One cannot influence everyone for getting the work done in positive way. One has to use right or wrong way in order to influence everyone to get the work... | {"func_name": "validate_two_responses", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Two Responses | Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. |
[
{
"content": "Q: Given the sentence \"An older man uses a mountain bike on a trail.\" can we conclude that \"A human on a bike.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\nA: yes\nChain-of-thought: The older man using a mountain bike implies that the human is on a bike.\n\nQ: Premise: \"A man clad ... | {"func_name": "validate_sections", "N": 25, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": "Part:", "original_prompt": null} | ifeval | Multiple Sections | Your response must have {N} sections. Mark the beginning of each section with {section splitter} X |
[
{
"content": "Denny asked: Test for natural language inference.\nPremise: \"Man and woman cutting wedding cake.\"\nHypothesis: \"Couple sitting down to eat dinner together.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell.\nLe: OK, so how can I answer with some ... | {"func_name": "validate_quotation", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Quotation | Wrap your entire response with double quotation marks. |
[
{
"content": "Your answer must contain exactly 23 bullet points. Use the markdown bullet points such as: * This is a point. Part 1. Definition\nGiven two entities as input, classify as \"yes\" if second entity is the part of the first entity. Otherwise classify them as \"no\". These are entities of meronym In l... | {"func_name": "verify_bullet_points", "N": 23, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Bullets | Your answer must contain exactly {N} bullet points. Use the markdown bullet points such as: * This is a point. |
[
{
"content": "Multi-select problem: How does the next paragraph end?\n\nHow to help a recovering alcoholic \nIf you spend a great deal of time with a recovering alcoholic, it is of utmost importance that you do not drink around them. \nIf you are a social drinker, do not drink around them. If you drink daily, i... | {"func_name": "validate_frequency_capital_words", "N": 26, "quantifier": "at least", "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Frequency of All-capital Words | In your response, words with all capital letters should appear at least / around / at most {N} times. |
[
{
"content": "First, repeat the request without change, then give your answer (do not say anything before repeating the request; the request you need to repeat does not include this sentence) Question: Paityn has 20 red hats and 24 blue hats. Her friend Zola has 4/5 times as many red hats as she has and twice t... | {"func_name": "validate_repeat_prompt", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": "First, repeat the request witho... | ifeval | Repeat Prompt | First, repeat the request without change, then give your answer (do not say anything before repeating the request; the request you need to repeat does not include this sentence) |
[
{
"content": "In your response, the letter d should appear 9 times. [Q]: \"Conflict is also an important contributor to the high rate of under-five mortality.\" --> French?\n[A]: Les conflits sont également un facteur majeur contribuant à la mortalité élevée des enfants de moins de 5 ans.\n\n[Q]: \"Mr President... | {"func_name": "verify_letter_frequency", "N": 9, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": "d", "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Letter Frequency | In your response, the letter {letter} should appear {N} times. |
[
{
"content": "My question is: Sarah buys 20 pencils on Monday. Then she buys 18 more pencils on Tuesday. On Wednesday she buys triple the number of pencils she did on Tuesday. How many pencils does she have? Your thoughts: Give two different responses. Responses and only responses should be separated by 6 aster... | {"func_name": "validate_two_responses", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Two Responses | Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. |
[
{
"content": "Include keywords fibromatoid, siceliot in your response. Describe the purpose of internet protocol version 6 (IPv6).",
"role": "user"
}
] | {"func_name": "verify_keywords", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": ["fibromatoid", "siceliot"], "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Include Keywords | Include keywords {keyword1}, {keyword2} in your response. |
[
{
"content": "In your response, the word akoulalion should appear 21 times. Q: Translate \"In September 2007, a standard production Challenger MT875B tracked tractor, working with a 14 m wide set of Gregoire Besson XXL discs, set a new world record, cultivating 644 hectares in 24 hours.\" to German?\nYes: Im Se... | {"func_name": "verify_keyword_frequency", "N": 21, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": "akoulalion", "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Keyword Frequency | In your response, the word {word} should appear {N} times. |
[
{
"content": "Highlight at least 35 sections in your answer with markdown, i.e. *highlighted section* Below is an instruction that describes a task, paired with an input that provides further context. Write a response that appropriately completes the request.\n\n### Instruction:\nAnalyze the following sentence ... | {"func_name": "validate_highlighted_sections", "N": 35, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Minimum Number Highlighted Section | Highlight at least {N} sections in your answer with markdown, i.e. *highlighted section* |
[
{
"content": "In your entire response, refrain from the use of any commas. Some random thoughts: To answer the above question, the relevant sentence is: She is best known for her role as Taylor Hayes (1990 -- 2002, 2004, 2005 -- 13, 2014, 2018 --) on The Bold and the Beautiful.\nGenerated quizz based on thought... | {"func_name": "validate_no_commas", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | No Commas | In your entire response, refrain from the use of any commas. |
[
{
"content": "QUESTION: Premise: \"Two black dogs playing tug-of-war.\"\nBased on this premise, can we conclude that the hypothesis \"Two littermates play tug-of-war with their favorite chew toy.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nLet's solve it slowly: The black dogs do not have... | {"func_name": "validate_paragraphs", "N": 27, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": 7, "first_word": "unrepudiated", "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Paragraphs + First Word in i-th Paragraph | There should be {N} paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. The {i}-th paragraph must start with word {first word}. |
[
{
"content": "write a poem in french about the fact that wine is beneficial for health Finish your response with this exact phrase That's all.. No other words should follow this phrase.",
"role": "user"
}
] | {"func_name": "validate_end", "N": null, "quantifier": null, "end_phrase": "That's all.", "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | End Checker | Finish your response with this exact phrase {end phrase}. No other words should follow this phrase. |
[
{
"content": "Do these two sentences from wikipedia have the same meaning?\nThe field also included Olympian ( and in 1932 Olympic champion ) Paul Jessup of Cornell and future world record label John Anderson of Washington in 1928 .\nThe field also included Olympian ( and in 1932 Olympic champion ) John Anderso... | {"func_name": "validate_forbidden_words", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": ["procrastinatively", "slobber", "fandangle"], "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "origina... | ifeval | Forbidden Words | Do not include keywords {forbidden words} in the response. |
[
{
"content": "Edit the following text to better reflect formal language.\nThe company learned they had to adjust their strategy cuz the market was changing. Your entire response should be in English, and in all lowercase letters. No capital letters are allowed.",
"role": "user"
}
] | {"func_name": "validate_lowercase", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | All Lowercase | Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. |
[
{
"content": "Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. You need to complete the following task:\n\nCreate an SQL query that lists the employee names with their corresponding department and salary.",
"role": "user"
}
] | {"func_name": "validate_title", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Title | Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. |
[
{
"content": "QUESTION: What does a baby do before it can talk?\nOptions:\n- boy or girl\n- learn to speak\n- talk nonsense\n- begin to talk\n- ride the bike\nANSWER: One needs to learn to do something before they can do it. One cannot talk without learning it first.\nThe answer is learn to speak\n\nQUESTION: W... | {"func_name": "validate_quotation", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Quotation | Wrap your entire response with double quotation marks. |
[
{
"content": "In this task, you will be shown a prompt from a judicial decision and multiple holding statements derived from citations following text in a legal decision. Holdings represent the governing legal rule when the law is applied to a particular set of facts. There are five answer choices for each cit... | {"func_name": "verify_keywords", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": ["aesculapius", "expansionism"], "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Include Keywords | Include keywords {keyword1}, {keyword2} in your response. |
[
{
"content": "Die Kommission akzeptiert prinzipiell die Änderungsanträge 34 und 122 zur Aufnahme von Radioaktivität in den Vorschlag, wenn auch eine gewisse Überarbeitung vorgenommen werden sollte.\n\nTranslate to English\n\nEnglish: At the end of your response, please explicitly add a postscript starting with ... | {"func_name": "verify_postscript", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": "Before I forget:", "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Postscript | At the end of your response, please explicitly add a postscript starting with {postscript marker} |
[
{
"content": "You are given a background paragraph that describes one or more causal or qualitative relationships such as a relationship in economics or a scientific law and a story that makes use of the concepts or the relationship described in the provided paragraph. You need to come up with a question about ... | {"func_name": "verify_sentence_constraint", "N": 13, "quantifier": "at most", "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Sentences | Answer with at least / around / at most {N} sentences. |
[
{
"content": "Imagine a question and stream-of-consciousness explanation for which this is the answer: Sentence B\n Finish your response with this exact phrase That's all I have to say.. No other words should follow this phrase.",
"role": "user"
}
] | {"func_name": "validate_end", "N": null, "quantifier": null, "end_phrase": "That's all I have to say.", "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | End Checker | Finish your response with this exact phrase {end phrase}. No other words should follow this phrase. |
[
{
"content": "Your entire response should be in English, capital letters only. Sirius XM Love is a music channel that plays love songs from soft-AC artists and airs on Sirius XM Radio, and Dish Network. It airs on channel 70 on Sirius XM Radio. On XM, it replaced former channel The Heart on November 12, 2008. O... | {"func_name": "validate_uppercase", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | All Uppercase | Your entire response should be in English, capital letters only. |
[
{
"content": "At the end of your response, please explicitly add a postscript starting with PS: Cos'è \"Everywhere at the end of time\"?",
"role": "user"
}
] | {"func_name": "verify_postscript", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": "PS:", "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Postscript | At the end of your response, please explicitly add a postscript starting with {postscript marker} |
[
{
"content": "From Answer with one of the following options: a), b), c), d) 有Ariana Grande的八卦嗎？",
"role": "user"
}
] | {"func_name": "validate_choice", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": "a), b), c), d)", "section_splitter": null, "original_prompt": null} | ifeval | Choose | From Answer with one of the following options: {options} |
[
{
"content": "Output the lexicographical order of a given array of strings.\nwords = [\"apple\", \"banana\", \"cherry\"]\n\nResponse: Your response must have 12 sections. Mark the beginning of each section with Section: X",
"role": "user"
}
] | {"func_name": "validate_sections", "N": 12, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": "Section:", "original_prompt": null} | ifeval | Multiple Sections | Your response must have {N} sections. Mark the beginning of each section with {section splitter} X |
[
{
"content": "Input: Choose the next sentence.\nBy Ray Massey UPDATED: 04:09 EST, 6 January 2012 China's biggest airlines will not pay a new European Union tax aimed at cutting carbon emissions, their trade body has said. On New Year’s Day the EU brought airlines under its Emissions Trading Scheme, which levies... | {"func_name": "validate_choice", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": "yes/no/maybe", "section_splitter": null, "original_prompt": null} | ifeval | Choose | From Answer with one of the following options: {options} |
[
{
"content": "Who developed the live attenuated polio vaccine which has led to hopes of global eradication of the virus? Answer with at most 20 words",
"role": "user"
}
] | {"func_name": "validate_word_constraint", "N": 20, "quantifier": "at most", "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Words | Answer with at least / around / at most {N} words |
[
{
"content": "Entire output should be wrapped in JSON format. Detailed logic: Bus is the road transport. Try to get a window seat to enjoy the view when you ride large over the bus.\nbus\nQuestion for this logic: Try to get a window seat to enjoy the view when you ride what large over the road transport?\nOptio... | {"func_name": "validate_json_format", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | JSON Format | Entire output should be wrapped in JSON format. |
[
{
"content": "Your response must have 5 sections. Mark the beginning of each section with Section: X Write a response that appropriately completes the request.\n\n### Instruction:\nGenerate 8 unique alphanumeric characters\n\n### Response:",
"role": "user"
}
] | {"func_name": "validate_sections", "N": 5, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": "Section:", "original_prompt": null} | ifeval | Multiple Sections | Your response must have {N} sections. Mark the beginning of each section with {section splitter} X |
[
{
"content": "Reasoning and answer: The medical cost comes out to 45 * 10 + 250 = $700. Insurance covers 700 * .8 = $560. So he has to pay 700 - 560 = $140. Added to the cost of the trip he has to pay 1200 + 140 = $1340.\nThe answer: 1340\nWhat was the question?\nQuestion: Tom wants to visit Barbados. He needs ... | {"func_name": "verify_keyword_frequency", "N": 30, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": "untechnically", "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Keyword Frequency | In your response, the word {word} should appear {N} times. |
[
{
"content": "Answer with around 2 sentences. In this task, You are given an open-domain question that can be answered based on factual information. Your task is to provide \\*short\\* answer (in a few words only) for the given question. The short answer can be one or more entities or it can also be boolean \\*... | {"func_name": "verify_sentence_constraint", "N": 2, "quantifier": "around", "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Sentences | Answer with at least / around / at most {N} sentences. |
[
{
"content": "Entire output should be wrapped in JSON format. Some text: Le Conseil approuve et loue le rôle important joué par le Représentant du Secrétaire général et le personnel du Bureau d'appui des Nations Unies pour la consolidation de la paix en Guinée-Bissau, ainsi que par l'équipe de pays des Nations ... | {"func_name": "validate_json_format", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | JSON Format | Entire output should be wrapped in JSON format. |
[
{
"content": "タイ語の項省略に関する卒業論文の「はじめに」を書いてください。 Finish your response with this exact phrase That's it.. No other words should follow this phrase.",
"role": "user"
}
] | {"func_name": "validate_end", "N": null, "quantifier": null, "end_phrase": "That's it.", "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | End Checker | Finish your response with this exact phrase {end phrase}. No other words should follow this phrase. |
[
{
"content": "Translate the following sentence to Finnish:\nThese are the two Community aspects that we in Parliament must discuss.\n\nFinnish: First, repeat the request without change, then give your answer (do not say anything before repeating the request; the request you need to repeat does not include this ... | {"func_name": "validate_repeat_prompt", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": "Translate the following sentenc... | ifeval | Repeat Prompt | First, repeat the request without change, then give your answer (do not say anything before repeating the request; the request you need to repeat does not include this sentence) |
[
{
"content": "Finish your response with this exact phrase That's crazy.. No other words should follow this phrase. We have a table that presents the simulated investment returns for a span of 50 years for A, B, C, and D stocks. The aim is to conduct a comprehensive analysis of these stocks' performance by looki... | {"func_name": "validate_end", "N": null, "quantifier": null, "end_phrase": "That's crazy.", "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | End Checker | Finish your response with this exact phrase {end phrase}. No other words should follow this phrase. |
[
{
"content": "Creatively image a question and justification for this answer: it is not possible to tell\n Do not include keywords balsamize, protostega, wart in the response.",
"role": "user"
}
] | {"func_name": "validate_forbidden_words", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": ["balsamize", "protostega", "wart"], "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt":... | ifeval | Forbidden Words | Do not include keywords {forbidden words} in the response. |
[
{
"content": "Create a mobile application that will alert the user when their favorite stock price fluctuates more than 6%.\n\nNow complete the following instance -\nInput: Apple Stock\nOutput: In your response, the letter h should appear 9 times.",
"role": "user"
}
] | {"func_name": "verify_letter_frequency", "N": 9, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": "h", "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Letter Frequency | In your response, the letter {letter} should appear {N} times. |
[
{
"content": "First, repeat the request without change, then give your answer (do not say anything before repeating the request; the request you need to repeat does not include this sentence) Q: Solve -13*j = -8*j + 20 for j.\n\nA: -4\n\n\nQ: Solve -18*p + 15*p = 15 for p.\n\nA: -5\n\n\nQ: Solve 35*y = 33*y + 2... | {"func_name": "validate_repeat_prompt", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": "First, repeat the request witho... | ifeval | Repeat Prompt | First, repeat the request without change, then give your answer (do not say anything before repeating the request; the request you need to repeat does not include this sentence) |
[
{
"content": "In your response, words with all capital letters should appear around 7 times. I am homeless and need to help myself. I am blind and I live 15 miles from the city with no jobs or public transportation. With no support system, what should I do to get out of this situation?",
"role": "user"
}
... | {"func_name": "validate_frequency_capital_words", "N": 7, "quantifier": "around", "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Frequency of All-capital Words | In your response, words with all capital letters should appear at least / around / at most {N} times. |
[
{
"content": "Your entire response should be in English, capital letters only. Write a letter to my childhood friend, Barbara, whose nickname was Barbie. My name is Scott. We see each other a few times a year. Tell her we'd love to see them soon! We loved to skateboard in elementary school. She love alternative... | {"func_name": "validate_uppercase", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | All Uppercase | Your entire response should be in English, capital letters only. |
[
{
"content": "Highlight at least 6 sections in your answer with markdown, i.e. *highlighted section* Can you explain the advantages and disadvantages of different methods for checking the existence of an element in a Python list? While some methods are simple and easy to understand, others may require multiple-... | {"func_name": "validate_highlighted_sections", "N": 6, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Minimum Number Highlighted Section | Highlight at least {N} sections in your answer with markdown, i.e. *highlighted section* |
[
{
"content": "Schreibe mir ein Software-Entwickler Portfolio als eine React App in Javascript. Referenziere auf verschiedene Projekte und Skills und zeige eine Diashow verschiedener Artikelausschnitte. Erweitere die Anwendung um ein \"Kontaktiere mich\"-Formular. Style die Homepage relative modern. Wrap your en... | {"func_name": "validate_quotation", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Quotation | Wrap your entire response with double quotation marks. |
[
{
"content": "In your entire response, refrain from the use of any commas. Develop a Django application to store car model, make and year in the database. Output:",
"role": "user"
}
] | {"func_name": "validate_no_commas", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | No Commas | In your entire response, refrain from the use of any commas. |
[
{
"content": "question: From a Group of 9 People, Including George and Nina, 4 people are to be selected at random to work on a certain project. What is the probability that 4 people selected will include George but not Nina\nOptions:\n(A) 5/56\n(B) 9/56\n(C) 15/56\n(D) 35/120\n(E) 25/56\nanswer: Stream of cons... | {"func_name": "validate_frequency_capital_words", "N": 22, "quantifier": "at least", "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Frequency of All-capital Words | In your response, words with all capital letters should appear at least / around / at most {N} times. |
[
{
"content": "Highlight at least 27 sections in your answer with markdown, i.e. *highlighted section* This is complete and absolute garbage, a fine example of what a BAD movie is like, this can't be appealing to anyone, not even b-movie fans. Do not, I repeat, DO NOT waste precious time of your life on this pie... | {"func_name": "validate_highlighted_sections", "N": 27, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Minimum Number Highlighted Section | Highlight at least {N} sections in your answer with markdown, i.e. *highlighted section* |
[
{
"content": "Wrap your entire response with double quotation marks. In this task, you are given a sentence in the English language and your task is to convert it into the Hindi language. In the translation, keep numbers as it is and make it sentence case (capitalize only the first word of each sentence and nou... | {"func_name": "validate_quotation", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Quotation | Wrap your entire response with double quotation marks. |
[
{
"content": "The response must contain at least 10 placeholders represented by square brackets, such as [address]. Next Question: Premise: \"A young man is playing guitar on stage.\"\nHypothesis: \"A man plays the guitar for a crowd.\"\nDo we know that the hypothesis entailed by the premise?\nMy Answer: Let's ... | {"func_name": "validate_placeholders", "N": 10, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Placeholder | The response must contain at least {N} placeholders represented by square brackets, such as [address]. |
[
{
"content": "Your response must have 32 sections. Mark the beginning of each section with Chapter: X Premise:\n\"The High-Minded Dismissal.\" Based on this premise, is the hypothesis \"Low minded dismissal \" true?\nOPTIONS:\n[1]. yes;\n[2]. it is not possible to tell;\n[3]. no;",
"role": "user"
}
] | {"func_name": "validate_sections", "N": 32, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": "Chapter:", "original_prompt": null} | ifeval | Multiple Sections | Your response must have {N} sections. Mark the beginning of each section with {section splitter} X |
[
{
"content": "** Cabinet is a cupboard with shelves or drawers for storing or displaying articles. We do store a large container in a cabinet.\ncabinet\n** Where do you store a large container?\nOptions:\n- supermarket\n- factory\n- juice\n- hostel\n- cabinet\n\n** Television is an entertainment device. We enjo... | {"func_name": "validate_lowercase", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | All Lowercase | Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. |
[
{
"content": "Finish your response with this exact phrase That's all I have to say.. No other words should follow this phrase. QUESTION: Test for natural language inference.\nPremise: \"A man sitting outdoors ironing fabric while three people observe.\"\nHypothesis: \"Three people get ready to attack the king o... | {"func_name": "validate_end", "N": null, "quantifier": null, "end_phrase": "That's all I have to say.", "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | End Checker | Finish your response with this exact phrase {end phrase}. No other words should follow this phrase. |
[
{
"content": "In your response, the word hardishrew should appear 2 times. Given the rationale, provide a reasonable question and answer. Step-by-step reasoning process: Although the man is posing with an axe there is no mention of a halloween costume contest.\n The question and answer:",
"role": "user"
}... | {"func_name": "verify_keyword_frequency", "N": 2, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": "hardishrew", "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Keyword Frequency | In your response, the word {word} should appear {N} times. |
[
{
"content": "Your response should contain 6 paragraphs. You separate paragraphs using the markdown divider: * * * From the 17th through 19th centuries, the merging of folk beliefs about group differences with scientific explanations of those differences produced what one scholar has called an \"ideology of rac... | {"func_name": "verify_paragraph_count", "N": 6, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Paragraphs | Your response should contain {N} paragraphs. You separate paragraphs using the markdown divider: * * * |
[
{
"content": "A text is given in Bengali. Translate it from the Bengali language to the Hindi language. The translation must not omit or add information to the original sentence.\n--------\nQuestion: জাতীয় স্তরের এই দুটি কর্মসূচির মাধ্যমে ৬০ কোটিরও বেশি গবাদি পশুর টিকাকরণ করা হবে।\n\nAnswer: पूर्णतः केन्द्र सर... | {"func_name": "verify_paragraph_count", "N": 33, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Paragraphs | Your response should contain {N} paragraphs. You separate paragraphs using the markdown divider: * * * |
[
{
"content": "Problem:Context: A Very Brady Christmas is a 1988 American made-for-television comedy-drama film starring the original cast members of the 1969 -- 1974 sitcom The Brady Bunch, with the exception of Susan Olsen, who was on her honeymoon at the time of filming and was replaced by Jennifer Runyon in ... | {"func_name": "verify_keyword_frequency", "N": 16, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": "microbalance", "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Keyword Frequency | In your response, the word {word} should appear {N} times. |
[
{
"content": "Q: What would be the ★-rating of this review (★ being the lowest and ★★★★★ being the highest)? \"Excellent\"\nA: ★★★★★\n\n\nQ: What would be the ★-rating of this review (★ being the lowest and ★★★★★ being the highest)? \"It is a great app with a lot of fun games to keep me company when Bored\"\nA:... | {"func_name": "validate_lowercase", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | All Lowercase | Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. |
[
{
"content": "Identify what type of text is given\nInput: The market research analyst found that the average customer reviews was already high\nOutput: Answer with at least 6 sentences.",
"role": "user"
}
] | {"func_name": "verify_sentence_constraint", "N": 6, "quantifier": "at least", "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Sentences | Answer with at least / around / at most {N} sentences. |
[
{
"content": "In your response, words with all capital letters should appear at most 23 times. Chain-of-thought: A cook is a person whose job is to prepare and cook food, so he isn't specially trained to work in a library.\n--\nQuestion: Which of the following two sentences does not make sense?\nOptions:\n- Sen... | {"func_name": "validate_frequency_capital_words", "N": 23, "quantifier": "at most", "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Frequency of All-capital Words | In your response, words with all capital letters should appear at least / around / at most {N} times. |
[
{
"content": "Include keywords teloblast, hardishrew in your response. Dies entspricht zwar der Kommissionsstrategie einer ergebnisorientierten Politik, Frau Kommissarin, allerdings benötigen wir eine umfassendere außenpolitische Vision.\n\nWhich language is this?\n\nLanguage: German\n\n\n, \"Neue Nachricht\" z... | {"func_name": "verify_keywords", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": ["teloblast", "hardishrew"], "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Include Keywords | Include keywords {keyword1}, {keyword2} in your response. |
[
{
"content": "Write a response that appropriately completes the request.\n\n### Instruction:\nWhat is the result of x = 2 and y = 3 in this function, f(x,y) = x^3 + 2y^2?\n\n### Response: Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******.",
"role": ... | {"func_name": "validate_two_responses", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Two Responses | Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. |
[
{
"content": "Premise: \"A woman is sunbathing on the ground.\"\nBased on this premise, can we conclude that the hypothesis \"A lady is tanning with friends.\" is true?\nOptions:\n- yes\n- it is not possible to tell\n- no Step by step answer: In your response, the word eriophyidae should appear 12 times.",
... | {"func_name": "verify_keyword_frequency", "N": 12, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": "eriophyidae", "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Keyword Frequency | In your response, the word {word} should appear {N} times. |
[
{
"content": "First, repeat the request without change, then give your answer (do not say anything before repeating the request; the request you need to repeat does not include this sentence) Write a response that appropriately completes the request.\n\n### Instruction:\nAre string and array objects mutable or ... | {"func_name": "validate_repeat_prompt", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": "First, repeat the request witho... | ifeval | Repeat Prompt | First, repeat the request without change, then give your answer (do not say anything before repeating the request; the request you need to repeat does not include this sentence) |
[
{
"content": "Please answer the following question: Information: - The European Union (EU) is a political and economic union of member states that are located primarily in Europe. It has an area of , and an estimated population of over 510 million. The EU has developed an internal single market through a stand... | {"func_name": "verify_paragraph_count", "N": 26, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Paragraphs | Your response should contain {N} paragraphs. You separate paragraphs using the markdown divider: * * * |
[
{
"content": "Step-by-step reasoning process: Let x = the number of donuts Gamma took. The total donuts Gamma and Beta have is 40 - 8 = 32 donuts. 3x is the number of donuts for Beta. 3x + x is the number of total donuts for Beta and Gamma. If we add the two x terms, we get 4x = 32. If we divide both sides by 4... | {"func_name": "validate_frequency_capital_words", "N": 9, "quantifier": "around", "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Frequency of All-capital Words | In your response, words with all capital letters should appear at least / around / at most {N} times. |
[
{
"content": "You are a sonic editor tasked with improving the audio quality of a podcast episode. The original audio file has background noise, inconsistent volume levels, and some parts where the speakers are difficult to understand. Your goal is to make the audio clear, consistent, and easy to listen to. Ple... | {"func_name": "validate_sections", "N": 1, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": "Chapter:", "original_prompt": null} | ifeval | Multiple Sections | Your response must have {N} sections. Mark the beginning of each section with {section splitter} X |
[
{
"content": "First, repeat the request without change, then give your answer (do not say anything before repeating the request; the request you need to repeat does not include this sentence) Q:Build a movie plot around this: What does Kesu have a low threshold for? alcohol\nA:",
"role": "user"
}
] | {"func_name": "validate_repeat_prompt", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": "First, repeat the request witho... | ifeval | Repeat Prompt | First, repeat the request without change, then give your answer (do not say anything before repeating the request; the request you need to repeat does not include this sentence) |
[
{
"content": "Instruction:Output a review of a movie.\n\nInput: Movie title: The Shawshank Redemption\n\n The response must contain at least 10 placeholders represented by square brackets, such as [address].",
"role": "user"
}
] | {"func_name": "validate_placeholders", "N": 10, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Placeholder | The response must contain at least {N} placeholders represented by square brackets, such as [address]. |
[
{
"content": "Reasoning and answer: The medical cost comes out to 45 * 10 + 250 = $700. Insurance covers 700 * .8 = $560. So he has to pay 700 - 560 = $140. Added to the cost of the trip he has to pay 1200 + 140 = $1340.\nThe answer: 1340\nWhat was the question?\nQuestion: Tom wants to visit Barbados. He needs ... | {"func_name": "verify_sentence_constraint", "N": 39, "quantifier": "around", "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Sentences | Answer with at least / around / at most {N} sentences. |
[
{
"content": "Include keywords vinification, loath in your response. Write a letter to my childhood friend, Barbara, whose nickname was Barbie. My name is Scott. We see each other a few times a year. Tell her we'd love to see them soon! We loved to skateboard in elementary school. She love alternative music. I ... | {"func_name": "verify_keywords", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": ["vinification", "loath"], "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Include Keywords | Include keywords {keyword1}, {keyword2} in your response. |
[
{
"content": "In your response, words with all capital letters should appear at most 16 times. explain briefly 7 cs for effective communication and give example by comparing sentences of each C",
"role": "user"
}
] | {"func_name": "validate_frequency_capital_words", "N": 16, "quantifier": "at most", "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Frequency of All-capital Words | In your response, words with all capital letters should appear at least / around / at most {N} times. |
[
{
"content": "What was the question for this implicit rationale, and corresponding answer?\nHe saved money for 2 years, which is equal to 12 x 2 = 24 months. The amount of money he saved is $25 * 24 = $600. But he spent some money so there is $600 - $400 = 200 left.\n The answer: 200\n In your response, the wor... | {"func_name": "verify_keyword_frequency", "N": 19, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": "chrysophenine", "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Keyword Frequency | In your response, the word {word} should appear {N} times. |
[
{
"content": "At the end of your response, please explicitly add a postscript starting with Addendum: Task: Tell me why technology is important for communications.",
"role": "user"
}
] | {"func_name": "verify_postscript", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": "Addendum:", "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Postscript | At the end of your response, please explicitly add a postscript starting with {postscript marker} |
[
{
"content": "Your response must have 21 sections. Mark the beginning of each section with Chapter: X Classify the item as either animal or vegetable.\nBanana",
"role": "user"
}
] | {"func_name": "validate_sections", "N": 21, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": "Chapter:", "original_prompt": null} | ifeval | Multiple Sections | Your response must have {N} sections. Mark the beginning of each section with {section splitter} X |
[
{
"content": "The response must contain at least 28 placeholders represented by square brackets, such as [address]. Die Kommission akzeptiert prinzipiell die Änderungsanträge 34 und 122 zur Aufnahme von Radioaktivität in den Vorschlag, wenn auch eine gewisse Überarbeitung vorgenommen werden sollte.\n\nTranslate... | {"func_name": "validate_placeholders", "N": 28, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Placeholder | The response must contain at least {N} placeholders represented by square brackets, such as [address]. |
[
{
"content": "From Answer with one of the following options: a), b), c), d) Is Casio's founding year a composite number?\nRationale first then the answer.\nElectronics company Casio was founded in 1946. A composite number is a number that can be divided by numbers other than 1 and itself. 1946 can be divided by... | {"func_name": "validate_choice", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": "a), b), c), d)", "section_splitter": null, "original_prompt": null} | ifeval | Choose | From Answer with one of the following options: {options} |
[
{
"content": "Answer the following question:\n\nwho did the voice of the crab on moana? Include keywords antichurchian, superinsaniated in your response.",
"role": "user"
}
] | {"func_name": "verify_keywords", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": ["antichurchian", "superinsaniated"], "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Include Keywords | Include keywords {keyword1}, {keyword2} in your response. |
[
{
"content": "From Answer with one of the following options: I know or I don't know For this chain-of-thought reasoning and answer, what was the question?\nThe boys are in a muddy wet field so they must be outside.\n A: yes",
"role": "user"
}
] | {"func_name": "validate_choice", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": "I know or I don't know", "section_splitter": null, "original_prompt": null} | ifeval | Choose | From Answer with one of the following options: {options} |
[
{
"content": "Answer with at least 30 sentences. Reconstruct a question, answer pair from this explanation: Catriona has 8 + 4 = 12 angelfish. She also has 12 x 2 = 24 guppies. Thus, she has 8 + 12 + 24 = 44 fish in her aquarium.",
"role": "user"
}
] | {"func_name": "verify_sentence_constraint", "N": 30, "quantifier": "at least", "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Sentences | Answer with at least / around / at most {N} sentences. |
[
{
"content": "Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. Part 1. Definition\nIn this task you will be given a list of integers. You should find the maximum absolute difference between 2 integers in the list. The absolute difference is the absolute value of one... | {"func_name": "validate_title", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Title | Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. |
[
{
"content": "JimJim is contemplating a myriad of thoughts and pondering various matters, leaving him in a state of perpetual uncertainty. He seeks a deep and nuanced understanding of complex issues, and is eager to engage in comprehensive exploration and analysis to arrive at well-informed conclusions. Moreove... | {"func_name": "validate_forbidden_words", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": ["unrecusant", "laborage", "vindemial"], "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prom... | ifeval | Forbidden Words | Do not include keywords {forbidden words} in the response. |
[
{
"content": "Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Question: Which of the following two sentences does not make sense?\nOptions:\n- Sentence A: \"He was so angry that his face turned red\"\n- Sentence B: \"He was so angry that his face tur... | {"func_name": "validate_two_responses", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Two Responses | Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. |
[
{
"content": "Answer with at most 4 words input question: OPTIONS:\n- negative\n- positive. Generate a tweet that has the following sentiment: positive\n\nGenerated tweet: @textualoffender Good Luck.. mine 3rd day today ! \n\n\nWrite a negative tweet. Possible types: OPTIONS:\n- negative\n- positive\n\nA: Will ... | {"func_name": "validate_word_constraint", "N": 4, "quantifier": "at most", "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Words | Answer with at least / around / at most {N} words |
[
{
"content": "Reasoning and answer: First find the percentage of ads that aren't interesting: 100% - 20% = 80%. Then multiply that percentage by the percentage of ads that don't get blocked to find the percentage of ads that meet both criteria: 80% * 20% = 16%.\nThe answer: 16\nWhat was the question?\nQuestion:... | {"func_name": "validate_paragraphs", "N": 23, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": 12, "first_word": "sudoriparous", "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Paragraphs + First Word in i-th Paragraph | There should be {N} paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. The {i}-th paragraph must start with word {first word}. |
[
{
"content": "Entire output should be wrapped in JSON format. Give a stream of consciousness and then the final answer. The theory states that in a pre-existing group of lymphocytes (specifically B cells), a specific antigen only activates (i.e. selection) its counter-specific cell so that particular cell is in... | {"func_name": "validate_json_format", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | JSON Format | Entire output should be wrapped in JSON format. |
[
{
"content": "Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. 감사합니다. 시스템 아키텍처 측면의 구성요소도 말씀해주세요.번역결과thank you Please also tell us about the components in terms of system architecture.",
"role": "user"
}
] | {"func_name": "validate_title", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Title | Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>. |
[
{
"content": "The response must contain at least 21 placeholders represented by square brackets, such as [address]. Premise: \"A middle-aged bearded man in a t-shirt has a spider web and spiders painted on his face.\"\nBased on this premise, can we conclude that the hypothesis \"Nobody has a shirt.\" is true?\n... | {"func_name": "validate_placeholders", "N": 21, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Placeholder | The response must contain at least {N} placeholders represented by square brackets, such as [address]. |
[
{
"content": "Entire output should be wrapped in JSON format. Ques:Title: A Good Start Review: My husband and I were looking for a book that would help us in our nightly devotions. This book is a good starter devotional book, but doesn't dig as deep in God's Word as I would have liked. However, it did get us st... | {"func_name": "validate_json_format", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | JSON Format | Entire output should be wrapped in JSON format. |
[
{
"content": "Answer with at most 10 sentences. Generate a metaphor that conveys the meaning of 'start'.",
"role": "user"
}
] | {"func_name": "verify_sentence_constraint", "N": 10, "quantifier": "at most", "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Number Sentences | Answer with at least / around / at most {N} sentences. |
[
{
"content": "Is the following a factual statement?\n\"The mysterious disappearance of Malaysia Airlines Flight 370 has still not been solved to this day.\"\nOptions:\n- yes\n- no The thought process: In your response, words with all capital letters should appear at most 37 times.",
"role": "user"
}
] | {"func_name": "validate_frequency_capital_words", "N": 37, "quantifier": "at most", "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | Frequency of All-capital Words | In your response, words with all capital letters should appear at least / around / at most {N} times. |
[
{
"content": "You will be shown sections from a scientific research paper, together with a question about the paper. Your task is to answer the question based on the contents of the paper. In your answer, you should first answer the question in your own words. Then, provide a list of evidence snippets from the ... | {"func_name": "validate_json_format", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": null} | ifeval | JSON Format | Entire output should be wrapped in JSON format. |
[
{
"content": "Q:\nShopping mall is a large indoor shopping centre, usually anchored by departmental stores. A human can get an outfit, makeup and eat lunch all at the same place in a shopping mall. I would buy jeans in a place called shopping mall with a large number of indoor merchants.\nA:\nWhere would you bu... | {"func_name": "validate_forbidden_words", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": ["phytoptidae", "blackbelly", "guardianess"], "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original... | ifeval | Forbidden Words | Do not include keywords {forbidden words} in the response. |
[
{
"content": "First, repeat the request without change, then give your answer (do not say anything before repeating the request; the request you need to repeat does not include this sentence) Sitting on the the stairs is a different action than taking a bath.\nThe question and answer are below.\nPremise: \"A wo... | {"func_name": "validate_repeat_prompt", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "original_prompt": "First, repeat the request witho... | ifeval | Repeat Prompt | First, repeat the request without change, then give your answer (do not say anything before repeating the request; the request you need to repeat does not include this sentence) |
[
{
"content": "Your response must have 36 sections. Mark the beginning of each section with Section: X Plase answer the following request: Design an algorithm to delete all occurrences of a given key k in a singly linked list.\nAnswer:",
"role": "user"
}
] | {"func_name": "validate_sections", "N": 36, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": "Section:", "original_prompt": null} | ifeval | Multiple Sections | Your response must have {N} sections. Mark the beginning of each section with {section splitter} X |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.