OpenAIReview is an open-source, AI-assisted tool for reviewing academic papers, built by Chenhao Tan’s team at the Chicago Human+AI (CHAI) Lab, part of the University of Chicago Data Science Institute, to give any researcher paper feedback “for less than the cost of a coffee”. It processes a paper sequentially and keeps a running summary of its key claims, definitions and equations, which lets it catch inconsistencies across the whole paper. The team separates reviewing for quality, which gives formative feedback to authors, from reviewing for gatekeeping, which decides acceptance, and OpenAIReview is aimed at quality review.
Benefits & outcomes
- The University of Chicago write-up reports that the tool reaches 87% location coverage of the issues flagged by comparable tools.
Notes & quotes
- Researchers can inspect the prompts, adapt the tool to their field’s methodological standards, and use it throughout the writing process.
- The team is refining the platform and exploring ways for it to verify the claims in papers directly.
- Tan is cautious about automating gatekeeping, and argues that judgments about originality, significance and broader impact still need human reviewers.
- The project’s website lists papers from OpenAI’s math repository with passages flagged as possibly wrong, and invites the public to contribute reviews.
Publisher / company: University of Chicago
Date of case study: 2026
Status: Live
Built by: Research, non-profit or individual
Sources: