Ask and Retrieve Knowledge: Towards Proactive Asking with Imperfect Information in Medical Multi-turn Dialogues
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.
Authors
- Zhiying Tu (ORCID: https://orcid.org/0000-0001-8800-4513)
- Dianbo Sui (ORCID: https://orcid.org/0000-0002-5200-2265)
- Yangqin Jiang (ORCID: https://orcid.org/0009-0002-3936-1703)
- Shengwei Wang
- Bolin Zhang (ORCID: https://orcid.org/0000-0002-6315-1856)
- Dianhui Chu (ORCID: https://orcid.org/0000-0003-2973-7252)
Institutions
- Harbin Institute of Technology (CN)
- Weihai Science and Technology Bureau (CN)
- University of Hong Kong (HK)
Publication Details
- Published
- 2025-07-13
- DOI
- https://doi.org/10.1145/3726302.3729898
- Primary Topic
- Topic Modeling
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- National Natural Science Foundation of China