Zoom in, Zoom out, Reframe: Domain Experts’ Strategies for Addressing Non-Experts' Complex Questions
Year: 2025
Type: conference-paper
Abstract: Consumers rely on the Internet for information in expert domains such as healthcare and law.Large Language Models (LLMs) have the potential to increase access to expert knowledge.However, past research has not addressed how to handle certain aspects of complex questions that commonly occur in expert-layperson interactions.We conducted in-depth interviews with 26 experts across multiple domains to understand how they experience and respond to challenges associated with non-experts' questions.Results from a thematic analysis reveal three recurring strategies that experts across domains employ when fielding complex questions.Experts zoom in to clarify details of a broad information request, zoom out to address overly narrow questions or assumptions, and reframe when the underlying need is unstated or poorly represented.We discuss implications for the design and development of LLM-based experiences that facilitate access to expert information.
Authors: Beverly Freeman, Roma Ruparel, Laura M Vardoulakis
Institution: Google (United States)
Language: English
Subfield: Information Systems
Field: Computer Science
Domain: Physical Sciences
Open Access status: bronze
OpenAlex ID: W4409870251