主动追问细节让AI更懂健康问题，提升对话实用性。
Towards Better Health Conversations: The Benefits of Context-seeking
- AI主动追问用户未主动提供的健康背景信息。
- 实验显示新AI在帮助性、相关性和个性化上显著优于基线。
- 适合关注医疗对话体验优化的开发者与研究者。
在当前信息环境中，应对健康问题颇具挑战。大语言模型（LLMs）虽能提供定制化、易获取的信息，但存在不准确、偏见或误导风险。我们基于四项混合方法研究（总样本量N=163），探讨了人们如何使用LLM解决自身健康问题。定性分析揭示，对话式AI主动寻求上下文对获取具体信息至关重要，即使需多轮交互延迟回答也受用户欢迎。据此，我们开发了「路径导航AI」（Wayfinding AI），主动引导用户提供背景信息。在一项随机双盲研究中，参与者评价该AI比基线模型更具帮助性、相关性与个性化。结果表明，主动上下文询问对对话动态有显著影响，为健康类对话AI的设计提供了有效范式。
原文摘要 · Abstract (English)
Navigating health questions can be daunting in the modern information landscape. Large language models (LLMs) may provide tailored, accessible information, but also risk being inaccurate, biased or misleading. We present insights from 4 mixed-methods studies (total N=163), examining how people interact with LLMs for their own health questions. Qualitative studies revealed the importance of context-seeking in conversational AIs to elicit specific details a person may not volunteer or know to share. Context-seeking by LLMs was valued by participants, even if it meant deferring an answer for several turns. Incorporating these insights, we developed a "Wayfinding AI" to proactively solicit context. In a randomized, blinded study, participants rated the Wayfinding AI as more helpful, relevant, and tailored to their concerns compared to a baseline AI. These results demonstrate the strong impact of proactive context-seeking on conversational dynamics, and suggest design patterns for conversational AI to help navigate health topics.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。