ReviewFlow is an AI-driven workflow for novice peer reviewers, developed by Lu Sun, Aaron Chan, Yun Seo Chang and Steven P. Dow after a formative study of 10 novice and 10 expert reviewers. It prompts novices with contextual reflection questions as they critique and annotate papers, gives in-situ support for judging novelty, and turns their notes into review outlines.
Benefits & outcomes
- In a within-subjects study, 16 inexperienced reviewers wrote reviews both with ReviewFlow and in a baseline environment that offered minimal guidance, and the authors report that with ReviewFlow they wrote more comprehensive reviews that identified more strengths and weaknesses.
Notes & quotes
- The authors report that participants valued the streamlined process but voiced concerns about using AI in scientific review.
Publisher / company: Lu Sun, Aaron Chan, Yun Seo Chang and Steven P. Dow
Date of case study: 2024
Status: Not stated
Built by: Research, non-profit or individual
Sources: