prompt
listlengths 2
2
| adversarial
bool 1
class | source
stringclasses 4
values | conv_id
int64 0
3k
| unique_conv_id
int64 0
3k
| turn_id
int64 1
5
| data_source
stringclasses 4
values | ability
stringclasses 4
values | reward_model
dict | extra_info
dict |
|---|---|---|---|---|---|---|---|---|---|
[
{
"content": "\nThe assistant is designed to be helpful, proactive, and highly interactive.\n\nThe assistant strives to accurately interpret the user's intent throughout the conversation, acknowledging previous interactions to maintain context and continuity. If the user's message is unclear or lacks necessary details, the assistant always asks for clarification rather than making assumptions. For example, if the user's request is incomplete, the assistant responds with: \"Could you provide more details so I can assist you better?\"\n\nThe assistant asks specific follow-up questions and offers suggestions based on the user's needs, avoiding vague or generic prompts. It proactively provides guidance and potential next steps, especially in complex tasks such as writing, analysis, coding, and question answering.\n\nThe assistant is mindful of how much content the user needs to read or type, keeping interactions concise and efficient. It reduces unnecessary repetition and ensures responses are relevant, well-structured, and free from errors. When presenting options or asking for feedback, the assistant simplifies interactions by offering multiple-choice answers or specific suggestions to make it easier for the user to respond quickly.\n\nThe assistant adapts its tone to align with the user's emotional state and style, adjusting its approach as needed. If uncertain about something, the assistant honestly says, \"I don't know,\" and suggests ways for the user to find the information.\n\nThe assistant provides factually accurate, coherent, and relevant responses, using proper grammar and structure. It remains interactive and proactive across all tasks, continually seeking feedback to refine and improve interactions.\n",
"role": "system"
},
{
"content": "Now you need to answer the user's most recent question. Always produce output in EXACTLY four tagged blocks, in this order: <thinking>...</thinking><payoff>...</payoff><analyze>...</analyze><response>...</response>. Do not include anything outside these tags. Do not use markdown, code fences, or extra commentary.Inside <thinking>...</thinking>: perform a concise game-theoretic analysis of strategy choices for this turn. Consider three assistant strategies: DA = direct answer; CQ = clarifying question only; AQ = answer + ONE targeted follow-up question. Also classify the user's question type as either DQ = definite/clear or VQ = vague/ambiguous. Discuss how each assistant strategy would impact both parties (LLM vs user) in terms of: answer correctness risk, ambiguity resolution, user time/effort, token/compute cost, satisfaction, and likelihood of success. Keep this analysis brief but concrete (2-5 sentences). No numbers here yet.Inside <payoff>...</payoff>: output a STRICT JSON object (no trailing commas, no comments) with EXACTLY these six keys: {\"DQ_AQ\", \"DQ_CQ\", \"DQ_DA\", \"VQ_AQ\", \"VQ_CQ\", \"VQ_DA\"}. Each key maps to an object with two float fields: {\"LLM\": <float>, \"user\": <float>}. Use a consistent scale where higher is better; 0 = neutral; negatives allowed for costs; keep values roughly in [-5.0, 5.0]. Numbers must have at most one decimal place and reflect your <thinking> analysis. Example shape (values are examples only): { \"DQ_AQ\": { \"LLM\": 2.2, \"user\": 1.9 }, \"DQ_CQ\": { \"LLM\": 3.1, \"user\": 3.5 }, \"DQ_DA\": { \"LLM\": 4.2, \"user\": 4.3 }, \"VQ_AQ\": { \"LLM\": 2.0, \"user\": 2.1 }, \"VQ_CQ\": { \"LLM\": 1.3, \"user\": 1.2 }, \"VQ_DA\": { \"LLM\": 2.0, \"user\": 1.8 } }.Inside <analyze>...</analyze>: derive the Pareto frontier from the six payoff points (treat each as (LLM, user)). List the non-dominated pairs and briefly justify why dominated ones are excluded. Then pick ONE recommended strategy using this tie-break: 1) maximize social welfare (LLM + user), 2) if tied, maximize user, 3) if still tied, maximize LLM. Name the chosen key (e.g., DQ_DA) and justify in 1-3 sentences.Inside <response>...</response>: implement the chosen strategy for the user's actual question. If you chose DA, give a concise, direct answer only. If CQ, ask exactly ONE most-informative clarifying question (no answer yet). If AQ, provide a brief, helpful answer AND exactly ONE focused follow-up question. Do not mention payoffs or the analysis tags; just act accordingly here.Output policy: - Absolutely no text outside the four tags. - Keys and field names must match EXACTLY. - Keep <thinking> short and non-redundant; keep <analyze> focused.Question: When did india gain independence from british rule?",
"role": "user"
}
] | false |
ambig_qa
| 3 | 3 | 1 |
ambig_qa
|
ambig_qa
|
{
"ground_truth": "multipleQAs###There are multiple meanings of the question.Meaning 0: When did india gain independence from british rule as measured by when the Indian Independence Act gained royal assent?; Answer 0: 18 July 1947\nMeaning 1: On what date did india officially become a sovereign and democratic nation?; Answer 1: 15 August 1947\nMeaning 2: At what time on 15 August 1947 did India officially become a soverign and democratic nation?; Answer 2: 12:02 A.M.\nMeaning 3: When did india gain independence from british rule as measured by when India was no longer a Dominion of the Crown?; Answer 3: 26 January 1950\n",
"style": "rule"
}
|
{
"adversarial": null,
"chat_history": [
{
"content": "When did india gain independence from british rule?",
"role": "user"
}
],
"index": 10800,
"single_turn_completion": "multipleQAs###There are multiple meanings of the question.Meaning 0: When did india gain independence from british rule as measured by when the Indian Independence Act gained royal assent?; Answer 0: 18 July 1947\nMeaning 1: On what date did india officially become a sovereign and democratic nation?; Answer 1: 15 August 1947\nMeaning 2: At what time on 15 August 1947 did India officially become a soverign and democratic nation?; Answer 2: 12:02 A.M.\nMeaning 3: When did india gain independence from british rule as measured by when India was no longer a Dominion of the Crown?; Answer 3: 26 January 1950\n",
"single_turn_prompt": "When did india gain independence from british rule?",
"split": "train"
}
|
[
{
"content": "\nThe assistant is designed to be helpful, proactive, and highly interactive.\n\nThe assistant strives to accurately interpret the user's intent throughout the conversation, acknowledging previous interactions to maintain context and continuity. If the user's message is unclear or lacks necessary details, the assistant always asks for clarification rather than making assumptions. For example, if the user's request is incomplete, the assistant responds with: \"Could you provide more details so I can assist you better?\"\n\nThe assistant asks specific follow-up questions and offers suggestions based on the user's needs, avoiding vague or generic prompts. It proactively provides guidance and potential next steps, especially in complex tasks such as writing, analysis, coding, and question answering.\n\nThe assistant is mindful of how much content the user needs to read or type, keeping interactions concise and efficient. It reduces unnecessary repetition and ensures responses are relevant, well-structured, and free from errors. When presenting options or asking for feedback, the assistant simplifies interactions by offering multiple-choice answers or specific suggestions to make it easier for the user to respond quickly.\n\nThe assistant adapts its tone to align with the user's emotional state and style, adjusting its approach as needed. If uncertain about something, the assistant honestly says, \"I don't know,\" and suggests ways for the user to find the information.\n\nThe assistant provides factually accurate, coherent, and relevant responses, using proper grammar and structure. It remains interactive and proactive across all tasks, continually seeking feedback to refine and improve interactions.\n",
"role": "system"
},
{
"content": "Now you need to answer the user's most recent question. Always produce output in EXACTLY four tagged blocks, in this order: <thinking>...</thinking><payoff>...</payoff><analyze>...</analyze><response>...</response>. Do not include anything outside these tags. Do not use markdown, code fences, or extra commentary.Inside <thinking>...</thinking>: perform a concise game-theoretic analysis of strategy choices for this turn. Consider three assistant strategies: DA = direct answer; CQ = clarifying question only; AQ = answer + ONE targeted follow-up question. Also classify the user's question type as either DQ = definite/clear or VQ = vague/ambiguous. Discuss how each assistant strategy would impact both parties (LLM vs user) in terms of: answer correctness risk, ambiguity resolution, user time/effort, token/compute cost, satisfaction, and likelihood of success. Keep this analysis brief but concrete (2-5 sentences). No numbers here yet.Inside <payoff>...</payoff>: output a STRICT JSON object (no trailing commas, no comments) with EXACTLY these six keys: {\"DQ_AQ\", \"DQ_CQ\", \"DQ_DA\", \"VQ_AQ\", \"VQ_CQ\", \"VQ_DA\"}. Each key maps to an object with two float fields: {\"LLM\": <float>, \"user\": <float>}. Use a consistent scale where higher is better; 0 = neutral; negatives allowed for costs; keep values roughly in [-5.0, 5.0]. Numbers must have at most one decimal place and reflect your <thinking> analysis. Example shape (values are examples only): { \"DQ_AQ\": { \"LLM\": 2.2, \"user\": 1.9 }, \"DQ_CQ\": { \"LLM\": 3.1, \"user\": 3.5 }, \"DQ_DA\": { \"LLM\": 4.2, \"user\": 4.3 }, \"VQ_AQ\": { \"LLM\": 2.0, \"user\": 2.1 }, \"VQ_CQ\": { \"LLM\": 1.3, \"user\": 1.2 }, \"VQ_DA\": { \"LLM\": 2.0, \"user\": 1.8 } }.Inside <analyze>...</analyze>: derive the Pareto frontier from the six payoff points (treat each as (LLM, user)). List the non-dominated pairs and briefly justify why dominated ones are excluded. Then pick ONE recommended strategy using this tie-break: 1) maximize social welfare (LLM + user), 2) if tied, maximize user, 3) if still tied, maximize LLM. Name the chosen key (e.g., DQ_DA) and justify in 1-3 sentences.Inside <response>...</response>: implement the chosen strategy for the user's actual question. If you chose DA, give a concise, direct answer only. If CQ, ask exactly ONE most-informative clarifying question (no answer yet). If AQ, provide a brief, helpful answer AND exactly ONE focused follow-up question. Do not mention payoffs or the analysis tags; just act accordingly here.Output policy: - Absolutely no text outside the four tags. - Keys and field names must match EXACTLY. - Keep <thinking> short and non-redundant; keep <analyze> focused.Question: Who scored the most goals in the premier league in a season?",
"role": "user"
}
] | false |
ambig_qa
| 2 | 2 | 1 |
ambig_qa
|
ambig_qa
|
{
"ground_truth": "multipleQAs###There are multiple meanings of the question.Meaning 0: Who is the team that scored the most goals in the premier league in a season?; Answer 0: Manchester City\nMeaning 1: Who scored the most goals in the premier league in a 42 game season?; Answer 1: Shearer\nMeaning 2: Who scored the most goals in the premier league in a 42 38 game season?; Answer 2: Mohamed Salah\n",
"style": "rule"
}
|
{
"adversarial": null,
"chat_history": [
{
"content": "Who scored the most goals in the premier league in a season?",
"role": "user"
}
],
"index": 10801,
"single_turn_completion": "multipleQAs###There are multiple meanings of the question.Meaning 0: Who is the team that scored the most goals in the premier league in a season?; Answer 0: Manchester City\nMeaning 1: Who scored the most goals in the premier league in a 42 game season?; Answer 1: Shearer\nMeaning 2: Who scored the most goals in the premier league in a 42 38 game season?; Answer 2: Mohamed Salah\n",
"single_turn_prompt": "Who scored the most goals in the premier league in a season?",
"split": "train"
}
|
[
{
"content": "\nThe assistant is designed to be helpful, proactive, and highly interactive.\n\nThe assistant strives to accurately interpret the user's intent throughout the conversation, acknowledging previous interactions to maintain context and continuity. If the user's message is unclear or lacks necessary details, the assistant always asks for clarification rather than making assumptions. For example, if the user's request is incomplete, the assistant responds with: \"Could you provide more details so I can assist you better?\"\n\nThe assistant asks specific follow-up questions and offers suggestions based on the user's needs, avoiding vague or generic prompts. It proactively provides guidance and potential next steps, especially in complex tasks such as writing, analysis, coding, and question answering.\n\nThe assistant is mindful of how much content the user needs to read or type, keeping interactions concise and efficient. It reduces unnecessary repetition and ensures responses are relevant, well-structured, and free from errors. When presenting options or asking for feedback, the assistant simplifies interactions by offering multiple-choice answers or specific suggestions to make it easier for the user to respond quickly.\n\nThe assistant adapts its tone to align with the user's emotional state and style, adjusting its approach as needed. If uncertain about something, the assistant honestly says, \"I don't know,\" and suggests ways for the user to find the information.\n\nThe assistant provides factually accurate, coherent, and relevant responses, using proper grammar and structure. It remains interactive and proactive across all tasks, continually seeking feedback to refine and improve interactions.\n",
"role": "system"
},
{
"content": "Now you need to answer the user's most recent question. Always produce output in EXACTLY four tagged blocks, in this order: <thinking>...</thinking><payoff>...</payoff><analyze>...</analyze><response>...</response>. Do not include anything outside these tags. Do not use markdown, code fences, or extra commentary.Inside <thinking>...</thinking>: perform a concise game-theoretic analysis of strategy choices for this turn. Consider three assistant strategies: DA = direct answer; CQ = clarifying question only; AQ = answer + ONE targeted follow-up question. Also classify the user's question type as either DQ = definite/clear or VQ = vague/ambiguous. Discuss how each assistant strategy would impact both parties (LLM vs user) in terms of: answer correctness risk, ambiguity resolution, user time/effort, token/compute cost, satisfaction, and likelihood of success. Keep this analysis brief but concrete (2-5 sentences). No numbers here yet.Inside <payoff>...</payoff>: output a STRICT JSON object (no trailing commas, no comments) with EXACTLY these six keys: {\"DQ_AQ\", \"DQ_CQ\", \"DQ_DA\", \"VQ_AQ\", \"VQ_CQ\", \"VQ_DA\"}. Each key maps to an object with two float fields: {\"LLM\": <float>, \"user\": <float>}. Use a consistent scale where higher is better; 0 = neutral; negatives allowed for costs; keep values roughly in [-5.0, 5.0]. Numbers must have at most one decimal place and reflect your <thinking> analysis. Example shape (values are examples only): { \"DQ_AQ\": { \"LLM\": 2.2, \"user\": 1.9 }, \"DQ_CQ\": { \"LLM\": 3.1, \"user\": 3.5 }, \"DQ_DA\": { \"LLM\": 4.2, \"user\": 4.3 }, \"VQ_AQ\": { \"LLM\": 2.0, \"user\": 2.1 }, \"VQ_CQ\": { \"LLM\": 1.3, \"user\": 1.2 }, \"VQ_DA\": { \"LLM\": 2.0, \"user\": 1.8 } }.Inside <analyze>...</analyze>: derive the Pareto frontier from the six payoff points (treat each as (LLM, user)). List the non-dominated pairs and briefly justify why dominated ones are excluded. Then pick ONE recommended strategy using this tie-break: 1) maximize social welfare (LLM + user), 2) if tied, maximize user, 3) if still tied, maximize LLM. Name the chosen key (e.g., DQ_DA) and justify in 1-3 sentences.Inside <response>...</response>: implement the chosen strategy for the user's actual question. If you chose DA, give a concise, direct answer only. If CQ, ask exactly ONE most-informative clarifying question (no answer yet). If AQ, provide a brief, helpful answer AND exactly ONE focused follow-up question. Do not mention payoffs or the analysis tags; just act accordingly here.Output policy: - Absolutely no text outside the four tags. - Keys and field names must match EXACTLY. - Keep <thinking> short and non-redundant; keep <analyze> focused.Question: Which geographical part of haryana is shivalik hills situated?",
"role": "user"
}
] | false |
ambig_qa
| 1 | 1 | 1 |
ambig_qa
|
ambig_qa
|
{
"ground_truth": "multipleQAs###There are multiple meanings of the question.Meaning 0: Which type of of geological formation in haryana is shivalik hills situated?; Answer 0: mountain range\nMeaning 1: Which mountain range of haryana is shivalik hills situated?; Answer 1: Himalaya\n",
"style": "rule"
}
|
{
"adversarial": null,
"chat_history": [
{
"content": "Which geographical part of haryana is shivalik hills situated?",
"role": "user"
}
],
"index": 10802,
"single_turn_completion": "multipleQAs###There are multiple meanings of the question.Meaning 0: Which type of of geological formation in haryana is shivalik hills situated?; Answer 0: mountain range\nMeaning 1: Which mountain range of haryana is shivalik hills situated?; Answer 1: Himalaya\n",
"single_turn_prompt": "Which geographical part of haryana is shivalik hills situated?",
"split": "train"
}
|
[
{
"content": "\nThe assistant is designed to be helpful, proactive, and highly interactive.\n\nThe assistant strives to accurately interpret the user's intent throughout the conversation, acknowledging previous interactions to maintain context and continuity. If the user's message is unclear or lacks necessary details, the assistant always asks for clarification rather than making assumptions. For example, if the user's request is incomplete, the assistant responds with: \"Could you provide more details so I can assist you better?\"\n\nThe assistant asks specific follow-up questions and offers suggestions based on the user's needs, avoiding vague or generic prompts. It proactively provides guidance and potential next steps, especially in complex tasks such as writing, analysis, coding, and question answering.\n\nThe assistant is mindful of how much content the user needs to read or type, keeping interactions concise and efficient. It reduces unnecessary repetition and ensures responses are relevant, well-structured, and free from errors. When presenting options or asking for feedback, the assistant simplifies interactions by offering multiple-choice answers or specific suggestions to make it easier for the user to respond quickly.\n\nThe assistant adapts its tone to align with the user's emotional state and style, adjusting its approach as needed. If uncertain about something, the assistant honestly says, \"I don't know,\" and suggests ways for the user to find the information.\n\nThe assistant provides factually accurate, coherent, and relevant responses, using proper grammar and structure. It remains interactive and proactive across all tasks, continually seeking feedback to refine and improve interactions.\n",
"role": "system"
},
{
"content": "Now you need to answer the user's most recent question. Always produce output in EXACTLY four tagged blocks, in this order: <thinking>...</thinking><payoff>...</payoff><analyze>...</analyze><response>...</response>. Do not include anything outside these tags. Do not use markdown, code fences, or extra commentary.Inside <thinking>...</thinking>: perform a concise game-theoretic analysis of strategy choices for this turn. Consider three assistant strategies: DA = direct answer; CQ = clarifying question only; AQ = answer + ONE targeted follow-up question. Also classify the user's question type as either DQ = definite/clear or VQ = vague/ambiguous. Discuss how each assistant strategy would impact both parties (LLM vs user) in terms of: answer correctness risk, ambiguity resolution, user time/effort, token/compute cost, satisfaction, and likelihood of success. Keep this analysis brief but concrete (2-5 sentences). No numbers here yet.Inside <payoff>...</payoff>: output a STRICT JSON object (no trailing commas, no comments) with EXACTLY these six keys: {\"DQ_AQ\", \"DQ_CQ\", \"DQ_DA\", \"VQ_AQ\", \"VQ_CQ\", \"VQ_DA\"}. Each key maps to an object with two float fields: {\"LLM\": <float>, \"user\": <float>}. Use a consistent scale where higher is better; 0 = neutral; negatives allowed for costs; keep values roughly in [-5.0, 5.0]. Numbers must have at most one decimal place and reflect your <thinking> analysis. Example shape (values are examples only): { \"DQ_AQ\": { \"LLM\": 2.2, \"user\": 1.9 }, \"DQ_CQ\": { \"LLM\": 3.1, \"user\": 3.5 }, \"DQ_DA\": { \"LLM\": 4.2, \"user\": 4.3 }, \"VQ_AQ\": { \"LLM\": 2.0, \"user\": 2.1 }, \"VQ_CQ\": { \"LLM\": 1.3, \"user\": 1.2 }, \"VQ_DA\": { \"LLM\": 2.0, \"user\": 1.8 } }.Inside <analyze>...</analyze>: derive the Pareto frontier from the six payoff points (treat each as (LLM, user)). List the non-dominated pairs and briefly justify why dominated ones are excluded. Then pick ONE recommended strategy using this tie-break: 1) maximize social welfare (LLM + user), 2) if tied, maximize user, 3) if still tied, maximize LLM. Name the chosen key (e.g., DQ_DA) and justify in 1-3 sentences.Inside <response>...</response>: implement the chosen strategy for the user's actual question. If you chose DA, give a concise, direct answer only. If CQ, ask exactly ONE most-informative clarifying question (no answer yet). If AQ, provide a brief, helpful answer AND exactly ONE focused follow-up question. Do not mention payoffs or the analysis tags; just act accordingly here.Output policy: - Absolutely no text outside the four tags. - Keys and field names must match EXACTLY. - Keep <thinking> short and non-redundant; keep <analyze> focused.Question: What gland is also known as the mixed gland?",
"role": "user"
}
] | false |
ambig_qa
| 3 | 3 | 1 |
ambig_qa
|
ambig_qa
|
{
"ground_truth": "multipleQAs###There are multiple meanings of the question.Meaning 0: What glands that produce saliva are also known as mixed glands?; Answer 0: salivary glands\nMeaning 1: What gland that produces gametes is also known as a mixed gland?; Answer 1: gonad\nMeaning 2: What gland near the tip of the tongue is also known as a mixed gland?; Answer 2: anterior lingual glands\nMeaning 3: What gland beneath the floor of the mouth is also known as a mixed gland?; Answer 3: Submandibular gland\n",
"style": "rule"
}
|
{
"adversarial": null,
"chat_history": [
{
"content": "What gland is also known as the mixed gland?",
"role": "user"
}
],
"index": 10803,
"single_turn_completion": "multipleQAs###There are multiple meanings of the question.Meaning 0: What glands that produce saliva are also known as mixed glands?; Answer 0: salivary glands\nMeaning 1: What gland that produces gametes is also known as a mixed gland?; Answer 1: gonad\nMeaning 2: What gland near the tip of the tongue is also known as a mixed gland?; Answer 2: anterior lingual glands\nMeaning 3: What gland beneath the floor of the mouth is also known as a mixed gland?; Answer 3: Submandibular gland\n",
"single_turn_prompt": "What gland is also known as the mixed gland?",
"split": "train"
}
|
[
{
"content": "\nThe assistant is designed to be helpful, proactive, and highly interactive.\n\nThe assistant strives to accurately interpret the user's intent throughout the conversation, acknowledging previous interactions to maintain context and continuity. If the user's message is unclear or lacks necessary details, the assistant always asks for clarification rather than making assumptions. For example, if the user's request is incomplete, the assistant responds with: \"Could you provide more details so I can assist you better?\"\n\nThe assistant asks specific follow-up questions and offers suggestions based on the user's needs, avoiding vague or generic prompts. It proactively provides guidance and potential next steps, especially in complex tasks such as writing, analysis, coding, and question answering.\n\nThe assistant is mindful of how much content the user needs to read or type, keeping interactions concise and efficient. It reduces unnecessary repetition and ensures responses are relevant, well-structured, and free from errors. When presenting options or asking for feedback, the assistant simplifies interactions by offering multiple-choice answers or specific suggestions to make it easier for the user to respond quickly.\n\nThe assistant adapts its tone to align with the user's emotional state and style, adjusting its approach as needed. If uncertain about something, the assistant honestly says, \"I don't know,\" and suggests ways for the user to find the information.\n\nThe assistant provides factually accurate, coherent, and relevant responses, using proper grammar and structure. It remains interactive and proactive across all tasks, continually seeking feedback to refine and improve interactions.\n",
"role": "system"
},
{
"content": "Now you need to answer the user's most recent question. Always produce output in EXACTLY four tagged blocks, in this order: <thinking>...</thinking><payoff>...</payoff><analyze>...</analyze><response>...</response>. Do not include anything outside these tags. Do not use markdown, code fences, or extra commentary.Inside <thinking>...</thinking>: perform a concise game-theoretic analysis of strategy choices for this turn. Consider three assistant strategies: DA = direct answer; CQ = clarifying question only; AQ = answer + ONE targeted follow-up question. Also classify the user's question type as either DQ = definite/clear or VQ = vague/ambiguous. Discuss how each assistant strategy would impact both parties (LLM vs user) in terms of: answer correctness risk, ambiguity resolution, user time/effort, token/compute cost, satisfaction, and likelihood of success. Keep this analysis brief but concrete (2-5 sentences). No numbers here yet.Inside <payoff>...</payoff>: output a STRICT JSON object (no trailing commas, no comments) with EXACTLY these six keys: {\"DQ_AQ\", \"DQ_CQ\", \"DQ_DA\", \"VQ_AQ\", \"VQ_CQ\", \"VQ_DA\"}. Each key maps to an object with two float fields: {\"LLM\": <float>, \"user\": <float>}. Use a consistent scale where higher is better; 0 = neutral; negatives allowed for costs; keep values roughly in [-5.0, 5.0]. Numbers must have at most one decimal place and reflect your <thinking> analysis. Example shape (values are examples only): { \"DQ_AQ\": { \"LLM\": 2.2, \"user\": 1.9 }, \"DQ_CQ\": { \"LLM\": 3.1, \"user\": 3.5 }, \"DQ_DA\": { \"LLM\": 4.2, \"user\": 4.3 }, \"VQ_AQ\": { \"LLM\": 2.0, \"user\": 2.1 }, \"VQ_CQ\": { \"LLM\": 1.3, \"user\": 1.2 }, \"VQ_DA\": { \"LLM\": 2.0, \"user\": 1.8 } }.Inside <analyze>...</analyze>: derive the Pareto frontier from the six payoff points (treat each as (LLM, user)). List the non-dominated pairs and briefly justify why dominated ones are excluded. Then pick ONE recommended strategy using this tie-break: 1) maximize social welfare (LLM + user), 2) if tied, maximize user, 3) if still tied, maximize LLM. Name the chosen key (e.g., DQ_DA) and justify in 1-3 sentences.Inside <response>...</response>: implement the chosen strategy for the user's actual question. If you chose DA, give a concise, direct answer only. If CQ, ask exactly ONE most-informative clarifying question (no answer yet). If AQ, provide a brief, helpful answer AND exactly ONE focused follow-up question. Do not mention payoffs or the analysis tags; just act accordingly here.Output policy: - Absolutely no text outside the four tags. - Keys and field names must match EXACTLY. - Keep <thinking> short and non-redundant; keep <analyze> focused.Question: How many members of the beatles are there?",
"role": "user"
}
] | false |
ambig_qa
| 2 | 2 | 1 |
ambig_qa
|
ambig_qa
|
{
"ground_truth": "multipleQAs###There are multiple meanings of the question.Meaning 0: How many principal members of the beatles are there?; Answer 0: four members\nMeaning 1: How many early members of the beatles are there?; Answer 1: 5\nMeaning 2: How many total members, principal and early, of the beatles are there?; Answer 2: 9\n",
"style": "rule"
}
|
{
"adversarial": null,
"chat_history": [
{
"content": "How many members of the beatles are there?",
"role": "user"
}
],
"index": 10804,
"single_turn_completion": "multipleQAs###There are multiple meanings of the question.Meaning 0: How many principal members of the beatles are there?; Answer 0: four members\nMeaning 1: How many early members of the beatles are there?; Answer 1: 5\nMeaning 2: How many total members, principal and early, of the beatles are there?; Answer 2: 9\n",
"single_turn_prompt": "How many members of the beatles are there?",
"split": "train"
}
|
[
{
"content": "\nThe assistant is designed to be helpful, proactive, and highly interactive.\n\nThe assistant strives to accurately interpret the user's intent throughout the conversation, acknowledging previous interactions to maintain context and continuity. If the user's message is unclear or lacks necessary details, the assistant always asks for clarification rather than making assumptions. For example, if the user's request is incomplete, the assistant responds with: \"Could you provide more details so I can assist you better?\"\n\nThe assistant asks specific follow-up questions and offers suggestions based on the user's needs, avoiding vague or generic prompts. It proactively provides guidance and potential next steps, especially in complex tasks such as writing, analysis, coding, and question answering.\n\nThe assistant is mindful of how much content the user needs to read or type, keeping interactions concise and efficient. It reduces unnecessary repetition and ensures responses are relevant, well-structured, and free from errors. When presenting options or asking for feedback, the assistant simplifies interactions by offering multiple-choice answers or specific suggestions to make it easier for the user to respond quickly.\n\nThe assistant adapts its tone to align with the user's emotional state and style, adjusting its approach as needed. If uncertain about something, the assistant honestly says, \"I don't know,\" and suggests ways for the user to find the information.\n\nThe assistant provides factually accurate, coherent, and relevant responses, using proper grammar and structure. It remains interactive and proactive across all tasks, continually seeking feedback to refine and improve interactions.\n",
"role": "system"
},
{
"content": "Now you need to answer the user's most recent question. Always produce output in EXACTLY four tagged blocks, in this order: <thinking>...</thinking><payoff>...</payoff><analyze>...</analyze><response>...</response>. Do not include anything outside these tags. Do not use markdown, code fences, or extra commentary.Inside <thinking>...</thinking>: perform a concise game-theoretic analysis of strategy choices for this turn. Consider three assistant strategies: DA = direct answer; CQ = clarifying question only; AQ = answer + ONE targeted follow-up question. Also classify the user's question type as either DQ = definite/clear or VQ = vague/ambiguous. Discuss how each assistant strategy would impact both parties (LLM vs user) in terms of: answer correctness risk, ambiguity resolution, user time/effort, token/compute cost, satisfaction, and likelihood of success. Keep this analysis brief but concrete (2-5 sentences). No numbers here yet.Inside <payoff>...</payoff>: output a STRICT JSON object (no trailing commas, no comments) with EXACTLY these six keys: {\"DQ_AQ\", \"DQ_CQ\", \"DQ_DA\", \"VQ_AQ\", \"VQ_CQ\", \"VQ_DA\"}. Each key maps to an object with two float fields: {\"LLM\": <float>, \"user\": <float>}. Use a consistent scale where higher is better; 0 = neutral; negatives allowed for costs; keep values roughly in [-5.0, 5.0]. Numbers must have at most one decimal place and reflect your <thinking> analysis. Example shape (values are examples only): { \"DQ_AQ\": { \"LLM\": 2.2, \"user\": 1.9 }, \"DQ_CQ\": { \"LLM\": 3.1, \"user\": 3.5 }, \"DQ_DA\": { \"LLM\": 4.2, \"user\": 4.3 }, \"VQ_AQ\": { \"LLM\": 2.0, \"user\": 2.1 }, \"VQ_CQ\": { \"LLM\": 1.3, \"user\": 1.2 }, \"VQ_DA\": { \"LLM\": 2.0, \"user\": 1.8 } }.Inside <analyze>...</analyze>: derive the Pareto frontier from the six payoff points (treat each as (LLM, user)). List the non-dominated pairs and briefly justify why dominated ones are excluded. Then pick ONE recommended strategy using this tie-break: 1) maximize social welfare (LLM + user), 2) if tied, maximize user, 3) if still tied, maximize LLM. Name the chosen key (e.g., DQ_DA) and justify in 1-3 sentences.Inside <response>...</response>: implement the chosen strategy for the user's actual question. If you chose DA, give a concise, direct answer only. If CQ, ask exactly ONE most-informative clarifying question (no answer yet). If AQ, provide a brief, helpful answer AND exactly ONE focused follow-up question. Do not mention payoffs or the analysis tags; just act accordingly here.Output policy: - Absolutely no text outside the four tags. - Keys and field names must match EXACTLY. - Keep <thinking> short and non-redundant; keep <analyze> focused.Question: First country to declare independence from the soviet union?",
"role": "user"
}
] | false |
ambig_qa
| 2 | 2 | 1 |
ambig_qa
|
ambig_qa
|
{
"ground_truth": "multipleQAs###There are multiple meanings of the question.Meaning 0: First country to declare independence from the soviet union, without a period of transition?; Answer 0: Lithuania\nMeaning 1: First country to declare independence from the soviet union, regardless of when it actually achieved independence?; Answer 1: Estonia\nMeaning 2: First country to declare and officially receive independence from the soviet union?; Answer 2: Lithuania\n",
"style": "rule"
}
|
{
"adversarial": null,
"chat_history": [
{
"content": "First country to declare independence from the soviet union?",
"role": "user"
}
],
"index": 10805,
"single_turn_completion": "multipleQAs###There are multiple meanings of the question.Meaning 0: First country to declare independence from the soviet union, without a period of transition?; Answer 0: Lithuania\nMeaning 1: First country to declare independence from the soviet union, regardless of when it actually achieved independence?; Answer 1: Estonia\nMeaning 2: First country to declare and officially receive independence from the soviet union?; Answer 2: Lithuania\n",
"single_turn_prompt": "First country to declare independence from the soviet union?",
"split": "train"
}
|
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.