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.
@article{arxiv.2510.18880,
title = {Towards Better Health Conversations: The Benefits of Context-seeking},
author = {Rory Sayres and Yuexing Hao and Abbi Ward and Amy Wang and Beverly Freeman and Serena Zhan and Diego Ardila and Jimmy Li and I-Ching Lee and Anna Iurchenko and Siyi Kou and Kartikeya Badola and Jimmy Hu and Bhawesh Kumar and Keith Johnson and Supriya Vijay and Justin Krogue and Avinatan Hassidim and Yossi Matias and Dale R. Webster and Sunny Virmani and Yun Liu and Quang Duong and Mike Schaekermann},
journal= {arXiv preprint arXiv:2510.18880},
year = {2025}
}