messages listlengths 1 1 | ground_truth stringlengths 285 19k | dataset stringclasses 1
value | constraint_type stringclasses 24
values | constraint stringclasses 24
values |
|---|---|---|---|---|
[
{
"content": "In your response, words with all capital letters should appear at most 32 times. Washington (CNN) -- The Pacific island nation of Palau has agreed to take in 17 Chinese Muslims held at the U.S. prison camp at Guantanamo Bay, Cuba, the country's ambassador to the United States said Wednesday. The m... | {"func_name": "validate_frequency_capital_words", "N": 32, "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": "Reasoning & Answer: The man is a guy who is sitting in a chair and getting a shave.\nyes\nQuestion: If \"A guy sitting in a chair is getting a shave.\" does that mean that \"The man sitting is getting a shave.\"?\nOptions:\n- yes\n- it is not possible to tell\n- no\n\nReasoning & Answer: Sentence ... | {"func_name": "verify_keyword_frequency", "N": 18, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": "haloa", "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": "What is the most logical next event?\n\nHow to pack for a whale watching trip \nDress in layers. \nIt is usually colder out on the water than it is inland or even on the shore. You will want to wear several layers to keep yourself warm during your trip. Entire output should be wrapped in JSON form... | {"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": "In your response, the letter f should appear 37 times. Create a Python class \"Point\" that has two instance variables x and y.",
"role": "user"
}
] | {"func_name": "verify_letter_frequency", "N": 37, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": "f", "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": "learn this text: \nSystem\n\nThe System dispositions are typically generated by Genesys system, with only a couple of exceptions such as \"Skipped - Agent Skip\". Depending on which disposition it is, the lead may be rescheduled to be called right away or may be taken out of the system, dependin... | {"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": "Include keywords plectrum, kevel in your response. DhiWise is a automated code generator platform who is recently release Typescript feature, give some content for social media post",
"role": "user"
}
] | {"func_name": "verify_keywords", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": ["plectrum", "kevel"], "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": "You need to complete the following task:\n\nMake a silhouette of the given object.\n\nObject: Bird\n\nAnswer: There should be 7 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. The 2-th paragraph must start with word dentiscalp.",
"role": "user"
}
... | {"func_name": "validate_paragraphs", "N": 7, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": 2, "first_word": "dentiscalp", "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": "Wrap your entire response with double quotation marks. next question: What do waitresses refill?\nOptions:\n- ball stopped\n- coffee shop\n- stationery shop\n- cup\n- restaurant\nreasoning:",
"role": "user"
}
] | {"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 a title, wrapped in double angular brackets, such as <<poem of joy>>. In this task, five ordered key facts are given. All the given facts are expressed in natural language. Your job is to generate a story 100 to 1000 words long, that includes all the facts given as input i... | {"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": "Edit the sentence using parallelism.\n\nAdditional Context:\nHe likes to read books, listen to the music and go for a walk.\n\nAnswer: In your response, the letter h should appear 12 times.",
"role": "user"
}
] | {"func_name": "verify_letter_frequency", "N": 12, "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": "From Answer with one of the following options: a), b), c), d) 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_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": "Wrap your entire response with double quotation marks. Explain what \"deep learning\" means\nResponse:",
"role": "user"
}
] | {"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": "Wrap your entire response with double quotation marks. How can I keep myself safe while walking in the dark?",
"role": "user"
}
] | {"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": "¿Qué fue primero, el huevo o la gallina? Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******.",
"role": "user"
}
] | {"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": "Your answer must contain exactly 32 bullet points. Use the markdown bullet points such as: * This is a point. 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 ... | {"func_name": "verify_bullet_points", "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": 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": "Web search results:\n\n[1] \"Pérdida de audición y sordera Se dice que alguien sufre pérdida de audición cuando no es capaz de oír tan bien como una persona cuyo sentido del oído es normal, es decir, cuyo umbral de audición en ambos oídos es igual o mejor que 20 dB. La pérdida de audición puede se... | {"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": "Problem: This review is like what?\n\nReview:Brilliant movie. The drawings were just amazing. Too bad it ended before it begun. I´ve waited 21 years for a sequel, but nooooo!!!\n+++++++++\nA: positive\n\n\nProblem: This review is like what?\n\nReview:A very attractive and capable cast is lost in t... | {"func_name": "verify_keyword_frequency", "N": 31, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": "unlearnedly", "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": "IN: French:\n\n◦ risk management review and thereby review requirements to submitting CTA (i.e. expedited review for targeted populations where data is abundant);\nOUT: ◦ Examen de la gestion des risques et par conséquent examen des exigences de soumission d'applications d'essais cliniques (c.-à-d... | {"func_name": "verify_letter_frequency", "N": 15, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": "b", "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": "How do I add a validation to make sure the date string being passed to the method is in the ffg. format:\n```'YYYY-MM-DD'\n```\nif it's not, method should raise some sort of error Highlight at least 15 sections in your answer with markdown, i.e. *highlighted section*",
"role": "user"
}
] | {"func_name": "validate_highlighted_sections", "N": 15, "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": "Answer with at most 30 sentences. You will be shown sections from a scientific research paper, together with a question about the paper. Please print out a collection of quotations from the research paper which answer the question. Each quotation should be a contiguous span of text from the paper.... | {"func_name": "verify_sentence_constraint", "N": 30, "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": "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": "verify_paragraph_count", "N": 14, "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": "Possible tweet sentiments: Choices:\n 1). negative\n 2). positive\nWrite a tweet that is 2).. At the end of your response, please explicitly add a postscript starting with Addendum:",
"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": "Please answer the following question: - ru clubcaps is 119 - birth name is hendrik egnatius botha - birth date is 27 february 1958 - ru provincecaps is 179 - ru ntupdate is 11 august 2014 - ru nationalpoints is -lrb- 337 -rrb- - ru clubyears is 1987 -- 92 - ru nationalcaps i... | {"func_name": "verify_sentence_constraint", "N": 14, "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": "TASK DEFINITION: You are given a sentence in English. Your job is to translate the English sentence into Galician.\nPROBLEM: So by convention, they created a rule in which they borrowed the CK sound, \"\" ck \"\" sound, from the classical Greek in the form of the letter Kai.\n\nSOLUTION: Así que a... | {"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": "Question: Given the following passage \"Of the third Dalai Lama, China Daily states that the \"Ming dynasty showed him special favor by allowing him to pay tribute.\" China Daily then says that Sonam Gyatso was granted the title Dorjichang or Vajradhara Dalai Lama in 1587 [sic!], but China Daily ... | {"func_name": "verify_letter_frequency", "N": 28, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": "f", "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": "You have been tasked with creating a successful email marketing campaign for a niche audience. However, you have a limited budget and can only send a certain number of emails per day. Your goal is to optimize the campaign and increase the open and click-through rates as much as possible.\nTo achie... | {"func_name": "verify_letter_frequency", "N": 2, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": "g", "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": "Do not include keywords missemblance, oxidoreduction, delime in the response. Question: The garbage truck passes through Daniel's neighborhood on Tuesdays, Thursdays, and Saturdays. In each garbage collection, an average of 200 kg is taken. Due to obstruction in the roads leading to Daniel's neigh... | {"func_name": "validate_forbidden_words", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": ["missemblance", "oxidoreduction", "delime"], "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": "Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. Write a response that appropriately completes the request.\n\n### Instruction:\nGenerate a simile using the words 'rain' and 'sun'.\n\n### Response:",
"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": "Write the following list of characters into a correctly formed sentence: 2Identifyingtoanick Your answer must contain a title, wrapped in double angular brackets, such as <<poem of joy>>.",
"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": "Your answer must contain exactly 22 bullet points. Use the markdown bullet points such as: * This is a point. Suppose we have two strings as shown below:\nString 1: \"This house\"\nString 2: \"overlooking the lake\"\nWhat is the code in Python that combines the two strings into one sentence? The f... | {"func_name": "verify_bullet_points", "N": 22, "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": "Your response must have 6 sections. Mark the beginning of each section with Chapter: X Quiero que me proporciones un script en python que calcule el número primo que ocupa la posición 10.000 y que se ejecute en el menor tiempo posible",
"role": "user"
}
] | {"func_name": "validate_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": "Chapter:", "original_prompt": null} | ifeval | Multiple Sections | Your response must have {N} sections. Mark the beginning of each section with {section splitter} X |
[
{
"content": "Highlight at least 32 sections in your answer with markdown, i.e. *highlighted section* ## Question and Answer John had a lot of free time. He didn't enjoy television much but had no one to interact with, so he'd spend his free time doing what?\nOptions:\n- watch film\n- play cards\n- surf net\n- ... | {"func_name": "validate_highlighted_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": null, "original_prompt": null} | ifeval | Minimum Number Highlighted Section | Highlight at least {N} sections in your answer with markdown, i.e. *highlighted section* |
[
{
"content": "This is the relevant information: He is best known for his work on NBC's Saturday Night Live from 1979-1980, and again from 1985 -- 86, often as the character Father Guido Sarducci.\nDonald Andrew `` Don '' Novello\nPassage: Donald Andrew \"Don\" Novello (born January 1, 1943) is an American write... | {"func_name": "verify_letter_frequency", "N": 1, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": "b", "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": "Finish your response with this exact phrase That's it.. No other words should follow this phrase. 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": "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": "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 started in a good routine of sitting down together... | {"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": "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_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": "You will be shown sections from... | 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 answer must contain exactly 1 bullet points. Use the markdown bullet points such as: * This is a point. 천 마일의 여정은 첫 걸음부터 시작한다고 말하는 사람은",
"role": "user"
}
] | {"func_name": "verify_bullet_points", "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": 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": "Entire output should be wrapped in JSON format. As technology advances, job roles evolve, and new ones emerge. In light of this, how can traditional recruitment practices keep up with the changing job market?",
"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": "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) Teacher:In this task, you're given a statement and three sentences as choices. Your job is to determine the neutral choi... | {"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": "Order and shipping management services는 [SUCCESS]의 [Manage] 영역의 서비스라고 생각되네요. Payment gateway integration services는 왜 Startup과 Sell 두 군데에 모두 들어가있습니까? 목적에 더 잘 맞는 세부 비즈니스로 이동해주세요.\n 번역결과\n Order and shipping management services are considered services in the [Manage] area of [SUCCESS]. Why are Paym... | {"func_name": "validate_word_constraint", "N": 24, "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": "Instruction:Compute the mean and standard deviation for this set of numbers.\n\nInput: 2, 3, 7, 5\n\n Wrap your entire response with double quotation marks.",
"role": "user"
}
] | {"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": "Include keywords scratchproof, testatum in your response. Reasoning & Answer: A man in a costume stands in front of a crowd.\nyes\nQuestion: If \"A man in a complicated costume with a red mask is holding a torch in front of a crowd of people.\" does that mean that \"Many of whom have cameras.\"?\n... | {"func_name": "verify_keywords", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": ["scratchproof", "testatum"], "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": "Answer with at least 27 words Task: Sort elements of an array in descending order in Java.",
"role": "user"
}
] | {"func_name": "validate_word_constraint", "N": 27, "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 Words | Answer with at least / around / at most {N} words |
[
{
"content": "Creatively image a question and justification for this answer: it is not possible to tell\n Finish your response with this exact phrase Oh no.. No other words should follow this phrase.",
"role": "user"
}
] | {"func_name": "validate_end", "N": null, "quantifier": null, "end_phrase": "Oh no.", "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": "Based on the given context, craft a common-sense question, especially those that are LONG, INTERESTING, and COMPLEX. The goal is to write questions that are easy for humans and hard for AI machines! To create such questions, here are some suggestions: A. What may (or may not) be the plausible reas... | {"func_name": "verify_keywords", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": ["hebraize", "baglike"], "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": "Given the `sales_data` dataset, which contains sales information for a chain of retail stores, can we develop a function that calculates the average sales per store per week, taking into account different product categories? How can we incorporate geographical location into this analysis to determ... | {"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": "In your response, the word overmotor should appear 8 times. What are some advantages of using the Coulomb matrix as a feature vector in machine learning models for chemical and molecular systems?\n\n<!DOCTYPE html>\r\n<html>\r\n<head>\r\n\t<title>Coulomb Matrix in Machine Learning</title>\r\n</hea... | {"func_name": "verify_keyword_frequency", "N": 8, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": "overmotor", "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": "What is the coefficient of thermal expansion of a copper wire with a diameter of 0.5mm and a length of 1m, when subjected to a temperature increase of 50°C? Please provide the equation used to calculate the coefficient of thermal expansion and show all the necessary calculations. Additionally, can... | {"func_name": "validate_frequency_capital_words", "N": 38, "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 given a math word problem and you are supposed to make use of mathematical concepts like probability, combinatorics, linear equations, sequences/series, or simple operators like addition, subtraction, division, or multiplication to answer the given question. Choose the best option from the... | {"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": "You are given a math word probl... | 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": "Next Question: Can we conclude from \"A young boy in blue trunks plays in the water at an outdoor fountain with a brick foundation.\" that \"A boy with soaking clothes plays in the sun.\"?\nOptions:\n- yes\n- no\n- it is not possible to tell\nMy Answer: Let's think. Not all boys plays in the fount... | {"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": "Next Question: Can we conclude ... | 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": "Problem: only weeks after conservatives were swept into power , the militant core of their party has reopened a potentially divisive debate about abortion , just as party leaders are struggling to project a new image of tolerance and consensus .\n\nWhat is a very short summary of the above text?\n... | {"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 response must have 13 sections. Mark the beginning of each section with Chapter: X How would you modify the given Swift code to calculate the difference and quotient of two numbers instead of the sum and product? Additionally, instead of printing the results, how would you return them from th... | {"func_name": "validate_sections", "N": 13, "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": "Your response must have 8 sections. Mark the beginning of each section with Part: X Denny asked: Premise: \"A person is sitting at a computer working while people wait.\"\nHypothesis: \"A human sitting.\"\nDo we know that the hypothesis entailed by the premise?.\nLe: OK, so how can I answer with s... | {"func_name": "validate_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": "Part:", "original_prompt": null} | ifeval | Multiple Sections | Your response must have {N} sections. Mark the beginning of each section with {section splitter} X |
[
{
"content": "If \"Two people wearing helmets ride over the yellow and white flowers.\", does this mean that \"Ten people riding horses over flowers.\"? Answer with at least 23 sentences.",
"role": "user"
}
] | {"func_name": "verify_sentence_constraint", "N": 23, "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 2 times. Por favor, toma el siguiente texto y coloca los signos de puntuación más convenientes.\nLa gente no tiene idea para qué viene a la Tierra. ¿Qué es? Anda buscando ¿quién soy? Para qué vine Qué hay más allá ocupándose de... | {"func_name": "validate_frequency_capital_words", "N": 2, "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": "Do not include keywords unaristocratically, sensationist, brigantia in the response. Read the bio below and try to give details on perlita neilson 's: - death place - death date - birth date - name - birthname - birth place Bio: perlita neilson -lrb- born margaret phil... | {"func_name": "validate_forbidden_words", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": ["unaristocratically", "sensationist", "brigantia"], "letter": null, "i": null, "first_word": null, "postscript_marker": null, "options": null, "section_splitter": null, "o... | ifeval | Forbidden Words | Do not include keywords {forbidden words} in the response. |
[
{
"content": "Include keywords uncontradicted, linden in your response. What's an example of a movie review?",
"role": "user"
}
] | {"func_name": "verify_keywords", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": ["uncontradicted", "linden"], "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": "Q: Test for natural language inference.\nPremise: \"A man with a camera and a bookbag walking down a street.\"\nHypothesis: \"A man carries his laptop and suitcase as he walks down the road.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- no\n- it is not possible to tell\nA: A ma... | {"func_name": "validate_word_constraint", "N": 17, "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 to remove duplicates from a list in Python?\nResponse: Include keywords hyperdiapason, gardenable in your response.",
"role": "user"
}
] | {"func_name": "verify_keywords", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": ["hyperdiapason", "gardenable"], "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 letter c should appear 36 times. 천 마일의 여정은 첫 걸음부터 시작한다고 말하는 사람은",
"role": "user"
}
] | {"func_name": "verify_letter_frequency", "N": 36, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": "c", "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": "Your entire response should be in English, capital letters only. Question: Given the following passage \"Of the third Dalai Lama, China Daily states that the \"Ming dynasty showed him special favor by allowing him to pay tribute.\" China Daily then says that Sonam Gyatso was granted the title Dor... | {"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": "Explain the economic impact of an increasing global population.\n\nAnswer: Highlight at least 27 sections in your answer with markdown, i.e. *highlighted section*",
"role": "user"
}
] | {"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": "From Answer with one of the following options: yes/no/maybe Write a response that appropriately completes the request.\n\n### Instruction:\nHow to make an AJAX call using the jQuery library?\n\n### Response:",
"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": "yes/no/maybe", "section_splitter": null, "original_prompt": null} | ifeval | Choose | From Answer with one of the following options: {options} |
[
{
"content": "Answer with around 5 words Design a chatbot that can efficiently handle multiple user queries simultaneously without any conflicts or errors. The chatbot should be able to understand and respond to different queries without mixing up the context or providing incorrect information. Additionally, it... | {"func_name": "validate_word_constraint", "N": 5, "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 Words | Answer with at least / around / at most {N} words |
[
{
"content": "From Answer with one of the following options: I know or I don't know Write an SQL query that displays the 10 highest paid employees.",
"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": "Generate a question that has the following answer: Jack Rollins for the following movie plot: The film is inspired, as the credits say \"by the music and many lives of Bob Dylan\". We see a POV shoot of a performer walking out on a stage at his concert to perform, then it cuts to him riding his... | {"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": "There should be 30 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. The 17-th paragraph must start with word counterreligion. QUESTION: Can we conclude from \"Two black friends greet each other outside by kissing each others cheeks.\" that \"The friends ... | {"func_name": "validate_paragraphs", "N": 30, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": 17, "first_word": "counterreligion", "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": "Come up with a story about a customer who relies on data science for success.\n\n Answer with at most 12 sentences.",
"role": "user"
}
] | {"func_name": "verify_sentence_constraint", "N": 12, "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": "How can you further enhance the virtual reality experience simulating the Australian bushfires? Apart from giving users the ability to manipulate the fire's spread, evacuation protocols, and rescue operations, can you integrate more interactive features, such as illustrating the effects of the fir... | {"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": "Someone about to pass by a statue would be near the statue.\nThe question and answer are below.\nPremise: \"A young girl is walking up to a bridge near dusk and is about to pass by a statue.\"\nHypothesis: \"Young girl is walking near the statue.\"\nIs the hypothesis entailed by the premise?\nOpti... | {"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": "In your entire response, refrain from the use of any commas. an international tribunal to prosecute suspects in the slaying of former lebanese prime minister rafik hariri opened sunday with a moment 's silence and a pledge to impartially investigate the politically charged case .\n\nA summary abou... | {"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": "In your entire response, refrain from the use of any commas. On the couch is a man with two children all taking a nap.. So what could be the question?\nQuestion followed by answer: If \"A father and his two children are taking a nap on the couch.\" does that mean that \"Kids and their dad take a n... | {"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": "Highlight at least 26 sections in your answer with markdown, i.e. *highlighted section* ```ruby\r\nclass Hr\n def initialize\n @content = \"\"\n end\n\n def to_s\n <<~HTML\n <div class=\"border-b-2 border-gray-400 my-8 text-center\">\n <span class=\"inline-block relative\" sty... | {"func_name": "validate_highlighted_sections", "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 | Minimum Number Highlighted Section | Highlight at least {N} sections in your answer with markdown, i.e. *highlighted section* |
[
{
"content": "Premise: \"A woman wearing a black tank top.\"\nHypothesis: \"Jeans and black sneakers is sitting on a wall near a mountainside full of houses.\"\nIs the hypothesis entailed by the premise?\nOptions:\n- yes\n- it is not possible to tell\n- no A step-by-step solution is:\n There should be 15 paragr... | {"func_name": "validate_paragraphs", "N": 15, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": 15, "first_word": "unwaverable", "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": "Stream of consciousness rationale: T = 40/36 * 18/5 = 4 sec\nThe question and answer pair are described below.\n Do not include keywords antidromous, anacusia, gnatling in the response.",
"role": "user"
}
] | {"func_name": "validate_forbidden_words", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": ["antidromous", "anacusia", "gnatling"], "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: ******. Using an Excel table, can you provide a detailed analysis of the advantages and disadvantages of market economies and planned economies?\nPlease include factors such as efficiency, innovat... | {"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": "Your response must have 33 sections. Mark the beginning of each section with Part: X TASK DEFINITION: You are given a sentence in English. Your job is to translate the English sentence into Galician.\nPROBLEM: So by convention, they created a rule in which they borrowed the CK sound, \"\" ck \"\" ... | {"func_name": "validate_sections", "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": "Part:", "original_prompt": null} | ifeval | Multiple Sections | Your response must have {N} sections. Mark the beginning of each section with {section splitter} X |
[
{
"content": "Your entire response should be in English, capital letters only. Write a code that takes a list of numbers, and outputs the 10th largest value.\nmylist = [2, 4, 54, 31, 34, 77, 29, 11, 44, 78, 65, 23]",
"role": "user"
}
] | {"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": "Answer with around 3 sentences. Instruction: How can companies reduce their carbon footprint?\nOutput:",
"role": "user"
}
] | {"func_name": "verify_sentence_constraint", "N": 3, "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": "Your entire response should be in English, and in all lowercase letters. No capital letters are allowed. Q: Mme Lynne m'a posé une question concernant la différence de dénomination entre régions et pays.\n\nCould you please translate this to English?\nA: Mrs Lynne asked me about the differentiatio... | {"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": "רעיונות לטיול בבולוניה ובמילאנו Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******.",
"role": "user"
}
] | {"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": "The response must contain at least 30 placeholders represented by square brackets, such as [address]. Stream of consciousness rationale: T = 40/36 * 18/5 = 4 sec\nThe question and answer pair are described below.",
"role": "user"
}
] | {"func_name": "validate_placeholders", "N": 30, "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": "Give two different responses. Responses and only responses should be separated by 6 asterisk symbols: ******. Suggest ways to debug the following code\n\nx = 'Address'\n print(\"Topic:\", x)",
"role": "user"
}
] | {"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": "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) Leo: Given the sentence \"A boy is jumping a rail on his bicycle.\" is it true that \"A boy is showing off for his girlf... | {"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": "The people lifting something above their head are a group of cheerleaders lifting up two other cheerleaders.\nThe question and answer are below.\nPremise: \"A group of cheerleaders are lifting up two other cheerleaders above their heads.\"\nHypothesis: \"The people are lifting something above thei... | {"func_name": "verify_paragraph_count", "N": 29, "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": "Answer with at least 16 sentences. 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?\nOptions:\n- yes\n- it is not possible to tell\n- no A step-by-step ... | {"func_name": "verify_sentence_constraint", "N": 16, "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": "Include keywords unwaverable, faintheartedly in your response. You will be shown sections from a scientific research paper, together with a question about the paper. Please print out a collection of quotations from the research paper which answer the question. Each quotation should be a contiguous... | {"func_name": "verify_keywords", "N": null, "quantifier": null, "end_phrase": null, "keyword_list": ["unwaverable", "faintheartedly"], "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": "Finish your response with this exact phrase That's it.. No other words should follow this phrase. Can you help with this?\n\nWrite a Python code snippet that creates a dictionary containing the numbers 1 to 10 as the keys and their squares as the values.",
"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": "The response must contain at least 31 placeholders represented by square brackets, such as [address]. С 2000 года работает перформером в группе TanzLaboratorium (Киев).\n\nTranslate to English\n\nEnglish:",
"role": "user"
}
] | {"func_name": "validate_placeholders", "N": 31, "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": "There should be 19 paragraphs. Paragraphs and only paragraphs are separated with each other by two line breaks. The 3-th paragraph must start with word counterretreat. input: OPTIONS:\n- see Oscar run\n- watch Oscar sleep\n- eat with Oscar together\n- take Oscar for long walks Now, answer this que... | {"func_name": "validate_paragraphs", "N": 19, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": 3, "first_word": "counterretreat", "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": "Your answer must contain exactly 8 bullet points. Use the markdown bullet points such as: * This is a point. Task: Create a SQL query to find all rows from the table \"customer_orders\" that have a total price of more than $50.",
"role": "user"
}
] | {"func_name": "verify_bullet_points", "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 | Number Bullets | Your answer must contain exactly {N} bullet points. Use the markdown bullet points such as: * This is a point. |
[
{
"content": "From Answer with one of the following options: yes/no/maybe question: Write a brief sentence.\n\nanswer: The beard is gray.\n\nquestion: Write a brief sentence.\n\nanswer: The football players are eating at a restaurant and sleeping.\n\nquestion: Write a brief sentence.\n\nanswer: two women passin... | {"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": "Test dire a un client que mal probleme casse dans marchandise pas possible livrer a temps In your response, the word reinvent should appear 38 times.",
"role": "user"
}
] | {"func_name": "verify_keyword_frequency", "N": 38, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": "reinvent", "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]: \"Chapter 23\" --> French?\n[A]: Chapitre 23\n\n[Q]: \"Article 39 of the Charter of the United Nations allows the Security Council to take measures such as sanctions only “to maintain or restore international peace and security” after having determined “the existence of any threat to the peac... | {"func_name": "validate_paragraphs", "N": 29, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": null, "forbidden_words": null, "letter": null, "i": 21, "first_word": "aesculapius", "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": "In this task, five ordered key facts are given. All the given facts are expressed in natural language. Your job is to generate a story 100 to 1000 words long, that includes all the facts given as input in their order of appearance while expanding upon them to produce a broader, yet coherent, narra... | {"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": "In your response, the word stereochromically should appear 32 times. First calculate the number of seeds from the sunflowers by multiplying the number of sunflowers by the number of seeds per sunflower: 6 sunflowers * 9 seeds / sunflower = 54 seeds. Next calculate the number of seeds from the dand... | {"func_name": "verify_keyword_frequency", "N": 32, "quantifier": null, "end_phrase": null, "keyword_list": null, "word": "stereochromically", "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": "¿Es importante tener acceso a hablantes nativos de inglés para mejorar en la comprensión y el uso del idioma? ¿Hay alguna forma de encontrar conversaciones regulares con hablantes nativos, ya sea en persona o en línea? Answer with at most 6 sentences.",
"role": "user"
}
] | {"func_name": "verify_sentence_constraint", "N": 6, "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": "How can a web platform for service-oriented firms be designed with features that ensure sustained business success and longevity? In addition to ensuring the prioritization and integration of user experience, design templates, scalability, mobile responsiveness, loading speed, search engine optimi... | {"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": "Q: Is there a negative or positive tone to this product review? === Title: Over Priced, Poorly Edited Review: I had to buy this as a text for a course on Africa. It is poorly edited, including basic typos, missing words, and mistaken punctuation. Additionally, there are entire sections that repeat... | {"func_name": "validate_frequency_capital_words", "N": 27, "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": "Compare and contrast two theories of evolution.\n\n The response must contain at least 5 placeholders represented by square brackets, such as [address].",
"role": "user"
}
] | {"func_name": "validate_placeholders", "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": null, "original_prompt": null} | ifeval | Number Placeholder | The response must contain at least {N} placeholders represented by square brackets, such as [address]. |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.