{"slug": "what-makes-a-question-curious-measuring-model-curiosity-in-human-llm", "title": "What Makes a Question Curious? Measuring Model Curiosity in Human-LLM Interactions", "summary": "A study posted to arXiv (2610.33950v1) found that curiosity-oriented questions make up only 17-28% of all questions asked by large language models across four conversation datasets, even though such questions are linked to more exploratory and epistemically rich user responses. The researchers introduced a theory-grounded taxonomy separating curiosity-oriented questions from generic model questioning, and a human study found model curiosity can encourage exploration, particularly in advice, creative, and research contexts. The authors say the findings support building LLMs that ask more selectively to deepen exploration and human-AI collaboration.", "body_md": "arXiv:2610.33950v1 Announce Type: new \nAbstract: 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.", "url": "https://wpnews.pro/news/what-makes-a-question-curious-measuring-model-curiosity-in-human-llm", "canonical_source": "https://www.machinebrief.com/news/what-makes-a-question-curious-measuring-model-curiosity-in-h-rsos", "published_at": "2026-10-27 04:00:00+00:00", "updated_at": "2026-10-27 05:42:25.747328+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-research", "natural-language-processing"], "entities": ["arXiv", "Large language models"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/what-makes-a-question-curious-measuring-model-curiosity-in-human-llm", "markdown": "https://wpnews.pro/news/what-makes-a-question-curious-measuring-model-curiosity-in-human-llm.md", "text": "https://wpnews.pro/news/what-makes-a-question-curious-measuring-model-curiosity-in-human-llm.txt", "jsonld": "https://wpnews.pro/news/what-makes-a-question-curious-measuring-model-curiosity-in-human-llm.jsonld"}}