arXiv cs.CL· Angana Borah, Rachana Ramchandar, Inderjeet Nair, Rada Mihalcea·· 12 小时前AI 评分34
什么让提问更有好奇心？衡量人机交互中的模型好奇心
What Makes a Question Curious? Measuring Model Curiosity in Human-LLM Interactions
AI 导读
研究提出“模型好奇心”概念，即模型为揭示知识缺口、假设与替代方案而主动提问，并构建了区分好奇心导向问题与一般模型提问的理论分类体系。在四个对话数据集中，好奇心导向问题仅占全部问题的17-28%，但与用户更具探索性、认知更丰富的后续回应相关。人类研究显示，好奇心提问能促进探索，在建议、创意和研究场景中尤为明显。
正文
Abstract:Large language models increasingly act as partners in everyday communication. In these interactions, useful assistance may require not only answering, but also asking the right questions that surface knowledge gaps, assumptions, and alternatives. In this study, we refer to such epistemic question-asking as model curiosity, and introduce a theory-grounded taxonomy that distinguishes curiosity-oriented questions from generic model questioning. Across four conversation datasets, we find that curiosity-oriented questions remain rare (17-28% of all questions), but are associated with more exploratory and epistemically rich subsequent user responses, with varying patterns across datasets. We further conduct a human study to evaluate the usefulness of model curiosity, finding that curiosity can encourage exploration, especially in advice, creative, and research contexts. These findings have implications for building LLMs that ask more selectively to support deeper exploration and human-AI collaboration.
| Subjects: | Computation and Language (cs.CL); Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.33950 [cs.CL] |
| (or arXiv:2610.33950v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.33950 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Angana Borah [view email]
[v1]
Sat, 24 Oct 2026 23:33:21 UTC (1,027 KB)
来源：arXiv cs.CL · arxiv.org