Interdisciplinary researchers use generative ai to fill knowledge gaps
Orchestrating GenAI for Interdisciplinary Research
Human-Computer Interaction
Summary
When researchers work across multiple fields, they need to learn new topics quickly while keeping their core expertise. This paper studied how interdisciplinary researchers use generative AI tools to help with this challenge. The researchers use AI to fill in gaps in knowledge but still rely on their own judgment to discover new ideas. The study also found a tricky problem: the AI's answers are hardest to check for accuracy when the researchers need the most help. The authors suggest designing AI tools that match users' expertise and encourage combining knowledge from different fields.
What this means in practice
- •For ai tool developers: Create AI assistants that adapt verification steps based on users' expertise and encourage integrating insights from multiple disciplines.$Commercial implications: Enables development of smarter interdisciplinary research AI tools that improve user trust and output relevance, addressing specific user needs.
- •For knowledge management teams: Design workflows that combine human expertise with AI to fill knowledge gaps efficiently while maintaining quality checks.
Authors
Shirley Anugrah Hayati, Moyan Zhou, Patricia Anugrah Setiani, Ruizi Wang, Joseph Chee Chang, Dongyeop Kang
Abstract
As researchers tackle interdisciplinary problems, they face the need to deepen expertise in primary areas while rapidly acquiring knowledge in secondary domains. Generative AI (GenAI) is increasingly positioned to meet this need, from general-purpose chat assistants to Deep Research tools marketed as autonomous research agents. Prior work has examined how researchers use GenAI to support single-discipline or general research tasks. However, we know little about the goals and GenAI practices in interdisciplinary research. We conducted a longitudinal study and semi-structured interviews with 15 interdisciplinary researchers to examine how interdisciplinary researchers actually orchestrate GenAI. Findings show that researchers leaned on GenAI to fill knowledge gaps while maintaining epistemic agency for novelty discovery. We also uncovered an expertise paradox: GenAI outputs were hardest to verify when most needed. Our empirical insights motivate GenAI designs that calibrate verification to researchers' expertise, nudge toward cross-domain synthesis, and adapt prompting and outputs to disciplinary conventions.