Ask and Retrieve Knowledge: Towards Proactive Asking with Imperfect Information in Medical Multi-turn Dialogues
Bolin Zhang, Shengwei Wang, Yangqin Jiang, Dianbo Sui, Zhiying Tu, Dianhui Chu
2025Year
Abstract
Large language models (LLMs) cannot effectively collaborate with humans who provide imperfect information at the initial stage of the dialogue, unless they learn to proactively ask questions.
Ask about this paper
Ask your agent about it.
Lune has read the top-tier papers around this one, so every answer names the papers it rests on.
Related papers
- MediQ: Question-Asking LLMs and a Benchmark for Reliable Interactive Clinical ReasoningShuyue Stella Li, Vidhisha Balachandran, Shangbin Feng, Jonathan Ilgen et al.NeurIPS 2024 · 215 citations
- Grounded in Reality: Learning and Deploying Proactive LLM from Offline LogsFei Wei, Daoyuan Chen, Ce Wang, Yilun Huang et al.ICML 2026 · 2 citations
- Task Descriptors Help Transformers Learn Linear Models In-ContextRuomin Huang, Rong GeICLR 2025
- Instruct or Interact? Exploring and Eliciting LLMs' Capability in Code Snippet Adaptation Through Prompt EngineeringTanghaoran Zhang, Yue Yu, Xinjun Mao, Shangwen Wang et al.ICSE 2025 · 3 citations
- Talking to a Know-It-All GPT or a Second-Guesser Claude? How Repair reveals distinct Multi-Turn Behavior in LLMsClara Lachenmaier, Hannah Bultmann, Sina ZarrießACL 2026
