Saved in:
Bibliographic Details
Main Authors: Liu, Yiren, Sharma, Pranav, Oswal, Mehul Jitendra, Xia, Haijun, Huang, Yun
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2409.12538
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915378498633728
author Liu, Yiren
Sharma, Pranav
Oswal, Mehul Jitendra
Xia, Haijun
Huang, Yun
author_facet Liu, Yiren
Sharma, Pranav
Oswal, Mehul Jitendra
Xia, Haijun
Huang, Yun
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2409_12538
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle PersonaFlow: Designing LLM-Simulated Expert Perspectives for Enhanced Research Ideation
Liu, Yiren
Sharma, Pranav
Oswal, Mehul Jitendra
Xia, Haijun
Huang, Yun
Human-Computer Interaction
Artificial Intelligence
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.
title PersonaFlow: Designing LLM-Simulated Expert Perspectives for Enhanced Research Ideation
topic Human-Computer Interaction
Artificial Intelligence
url https://arxiv.org/abs/2409.12538