Clarification Question Generation

Ask about this topic

Overview

Clarification question generation studies how AI systems detect underspecified requests and ask questions that reveal the user’s intended meaning. Work spans conversational question answering, text-to-SQL, coding, recommendations, and tool-using agents, using methods such as uncertainty estimates, information gain, value-of-information reasoning, and reinforcement learning. Evaluation increasingly uses multi-turn benchmarks and human or simulated users to assess whether questions resolve intent, improve task outcomes, and avoid unnecessary turns. A central challenge is balancing the risks of guessing against the cost of interrupting users: models may recognize ambiguity yet fail to ask, or ask questions that do not change the outcome.

Latest papers

CardsList

40 papers11 papers in the last four weeks, up 120% on the four weeks before. 0.1% of all new papers.

  1. iPrefBench: A User-Centric Benchmark for Personalized Mobile Use Agents

    Oct 26, 2026Yuting Ning, Ruijia Cheng, Sushobhan Ghosh +7Personal AI AgentsMobile Agent Benchmarks

    The Ohio State University · Apple

  2. HerHealthGPT: An Evidence-Grounded Conversational AI System for Women's Reproductive Health Copy title

    Oct 24, 2026Hassan Saeed Hassan Albattra, Mazen Mohammed Bahgat, Rahatara Ferdousi +2HealthcareMedical QA

    School of Computing, Queen’s University, Kingston, Ontario, Canada

  3. A Small Model Asks Better: Fine-Tuning Query Clarification for Retrieval-Augmented Generation

    Oct 19, 2026Lihong He, Lucian Popa, Marina DanilevskyClarification Question GenerationRetrieval-Augmented Generation

    IBM Research, USA

  4. Probing Ambiguity: Adversarial Intent Resolution for Robust Text-to-SQL

    Oct 16, 2026Youbing Yin, Xujun Peng, Muhammad S. Uddin +3Text-to-SQLExecution-Guided Text-to-SQL

    Capital One

  5. LexPilot: Benchmarking the Proactive Interaction Ability of Legal LLMs with Laypeople in Chinese Civil Case Consultation

    Oct 16, 2026Wenbin Zhang, ShangZhan Li, Bingxiang He +5Legal NLPLLM Evaluation

    Harbin Institute of Technology · Tsinghua University

  6. When Reasoning Is Not Enough: Proactive Inquiry for Cross-Modal Safety in Multimodal Large Language Models

    Oct 15, 2026Wei Cai, Jian Zhao, Yuchen Yuan +1Multimodal Multi-Turn Safety AlignmentVLM Safety

    Institute of Artificial Intelligence (TeleAI), China Telecom, P. R. China. · Peking University. · School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi’an 710072, P. R. China.

  7. Don't Guess, Just Ask: Evaluating Interactive Requirement Clarification for Repository-Level Software Development

    Oct 9, 2026Mingyu Chen, Zhiqing Zhong, Manyi Wang +3Software Engineering BenchmarksClarification Question Generation

    The Chinese University of Hong Kong, Shenzhen, Guangdong, China

  8. CLEAT: Learning Value-Guided Clarification for Interactive Agents

    Oct 8, 2026Jiatan Huang, Zheyuan Zhang, Ziming Li +4LLM AgentsLLM Alignment

    University of Connecticut · University of Notre Dame · University of Massachusetts, Amherst

  9. Learning to Clarify Underspecified Intents Under Limited Interaction

    Oct 3, 2026Pranav M R, Manuel Cherep, Pattie Maes +1Human-AI InteractionClarification Question Generation

    BITS Pilani & MIT · MIT · Dartmouth College

  10. Beyond Correctness: Resolving Underspecification in Agentic Text-to-SQL

    Oct 2, 2026Wen-Zhi Li, Yue Gong, Konstantinos Kanellis +1Text-to-SQLClarification Question Generation

    Department of Computer Science Cornell University · Amazon Web Services

  11. CONTRA: Discovering and Qualifying Behavior-Changing Questions for Selective Clarification in LLM Code Generation

    Oct 1, 2026Zheng Fang, Yongmin Li, Yichang Zhang +5Clarification Question GenerationAI Coding Agents

    Peking University · Wuhan University

  12. Rational Clarification by Assistive Agents via Value-of-Information Reasoning

    Sep 29, 2026T. Duy Nguyen-Hien, Yee Whye Teh, Wee Sun Lee +1Value of InformationClarification Question Generation

    Department of Computer Science, National University of Singapore · Department of Statistics, University of Oxford · Agency for Science, Technology and Research (A*STAR)

  13. Clarify the User or Verify the World? Uncertainty Routing for Proactive Agents

    Sep 26, 2026Zhaofeng Li, Xuan Zhang, Xiaokui Xiao +1Proactive AgentsTool-Using Agents

    National University of Singapore · Singapore Management University

  14. When and How Should an Agent Clarify? CIGAsk: Teaching LLMs to Clarify via Counterfactual Information Gain

    Sep 21, 2026Yunxiang Li, Xixin Wu, Helen MengClarification Question GenerationLLM Agent Training

    The Chinese University of Hong Kong, Hong Kong SAR, China

  15. FinInteract: Benchmarking Clarification and Intent Integration in Ambiguous Financial Question Answering

    Sep 21, 2026Xinyu Wang, Tung Sum Thomas Kwok, Zhenghan Tai +1Financial QAFinancial Language Model Evaluation

    McGill University · University of California, Los Angeles · University of Toronto

  16. IdeaAMBIG: Benchmarking Implementation-Critical Gaps in Research-Idea Specifications

    Sep 9, 2026Yiling Ma, Yilun Zhao, Sihong Wu +2Benchmark DesignClarification Question Generation

    Yale University · TCS Research

  17. A Tri-Agent Framework for Evaluating and Aligning Question Clarification Capabilities of Large Language Models

    Sep 2, 2026Yikai Zhao, Saurabh Pandey, Pradeep Kumar MisraMulti-Agent LLM SystemsClarification Question Generation

    Amazon Dallas, Texas, USA · Amazon Seattle, Washington, USA

  18. PragAlign: Evidence-Sensitive Reply Assistance Across Chinese and Japanese Appropriateness Judgments

    Aug 27, 2026Xin Zhong, Satori HachisukaPragmatic Reasoning in Language ModelsCultural Alignment

    The University of Tokyo

  19. A knowledge-guided agentic framework for mitigating patient-context ambiguity in health queries

    Aug 20, 2026Mahyar Abbasian, Saba A. Farahani, Arshia Ilaty +3Medical QAClarification Question Generation

  20. Ask, Condition or Abstain: Reinforcement Learning for Missing-Premise Reasoning

    Aug 17, 2026Yongqi Tong, Zhenyu Zhang, Zimi Liu +8RL for Language Model ReasoningClarification Question Generation

    Ant International · Ant Group · Zhejiang University +1

  21. Do LLMs Know What to Ask and When? Evaluating Multi-Turn Information Seeking

    Aug 14, 2026Yepeng Huang, Jiawen Zhang, Michelle Dai +4LLM EvaluationClarification Question Generation

    Harvard University · Google DeepMind

  22. CLAIM: Leading Open-domain Active Clarification of Large Language Models with Uncertainty Measurement

    Aug 12, 2026Kuangzhao Yang, Ziliang Zhao, Zhicheng DouClarification Question Generation

    Gaoling School of Artificial Intelligence, Renmin University of China Beijing, China

  23. Personalized Deep Research Query Refinement with Graph-Scaffolded Evidence Grounding

    Aug 6, 2026Soojin Yoon, Dongha LeeDeep Research AgentsClarification Question Generation

    Department of Artificial Intelligence, Yonsei University

  24. CLARA: Clarification of Language Ambiguity through Result Analysis for Natural-Language Cancer Genomics Queries

    Aug 3, 2026Pratyush Kumar Shukla, Manveer Singh Tib, Siddhant GargCancer GenomicsClarification Question Generation

    Independent Researchers

  25. One More Turn, Less Regret: A Regret-Based Multi-Turn Benchmark for LLMs' Clarification Policies

    Jul 23, 2026Minh Ngoc Ta, My Anh Tran Nguyen, Duong D. Nguyen +2LLM EvaluationClarification Question Generation

    MBZUAI · BKAI Research Center, Hanoi University of Science and Technology · INSAIT, Sofia University "St. Kliment Ohridski"

  26. Clarify Before Executing: A Self-Evolving Agent for Resolving Intent Asymmetry in 3D Tool Orchestration

    Jul 17, 2026Xiaoye Zhu, Weixin Li, Junan Huo +53D Asset GenerationClarification Question Generation

    South China University of Technology Guangzhou, Guangdong, China

  27. GIST-CMTF: Goal-State Inference for Causal Minimal Tool Filtering in LLM Agents

    Jun 15, 2026Rahul Suresh Babu, Rohit ShuklaClarification Question GenerationTool-Using Agents

    Independent Researcher United States of America

  28. Uncertainty-Aware Clarification in LLM Agents with Information Gain

    Jun 2, 2026Mengyi Deng, Zhiwei Li, Xin Li +4Clarification Question GenerationTool-Using Agents

    Information Hub, HKUST(GZ) · Jilin University · et al.

  29. On Wednesdays, We Ask Questions: Optimizing "Active Listening" in Automated Legal Triage and Referral

    May 29, 2026Quinten Steenhuis, Jacqueline HarveyLegal NLPAI-Assisted Decision Making

    Suffolk University Law School Boston, United States of America

  30. Clarify, Abstain or Answer? Strategising in Conversation with Belief-Augmented Generation

    May 25, 2026Joris Baan, Wilker Aziz, Barbara Plank +1Clarification Question GenerationQuestion Answering

    University of Amsterdam · LMU Munich · European Commission, Joint Research Centre (JRC), Brussels