PersonaFlow: Designing LLM-Simulated Expert Perspectives for Enhanced Research Ideation
This addresses the challenge for researchers and innovators who need diverse expertise but face availability constraints, offering an incremental improvement in AI-augmented creativity tools.
The paper tackled the problem of limited access to domain experts for generating interdisciplinary research ideas by introducing PersonaFlow, a system that uses LLMs to simulate expert perspectives, resulting in increased perceived relevance and creativity of ideas and enhanced critical thinking without raising cognitive load.
Generating interdisciplinary research ideas requires diverse domain expertise, but access to timely feedback is often limited by the availability of experts. In this paper, we introduce PersonaFlow, a novel system designed to provide multiple perspectives by using LLMs to simulate domain-specific experts. Our user studies showed that the new design 1) increased the perceived relevance and creativity of ideated research directions, and 2) promoted users' critical thinking activities (e.g., interpretation, analysis, evaluation, inference, and self-regulation), without increasing their perceived cognitive load. Moreover, users' ability to customize expert profiles significantly improved their sense of agency, which can potentially mitigate their over-reliance on AI. This work contributes to the design of intelligent systems that augment creativity and collaboration, and provides design implications of using customizable AI-simulated personas in domains within and beyond research ideation.