Skip to main navigation Skip to search Skip to main content

All Accept, No Reject: Evaluating LLMs as "peer" Reviewers

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

An exponential rise in manuscript submission volume has strained the peer review system, prompting interest in automation from overburdened scholars and publishers. We systematically evaluated GPT-4.1, GPT-4o, o1, o3, o3-mini, and GPT-5 as "peer"reviewers, comparing their evaluation and acceptance of 137 manuscripts from an open dataset (PeerRead) with the corresponding human-generated reviews. While o3's and GPT-5's acceptance rates were close to the human benchmark (∼67% of submissions), others approved nearly every paper (>98%); all models performed extremely poorly on accuracy, precision, and recall metrics. To probe this striking "yes-bias", we profiled the LLMs using Schwartz's Portrait Values Questionnaire (PVQ-RR) and found that all LLMs emphasized self-transcendence and openness-to-change and de-emphasized conservation and self-enhancement. We argue that value orientations of LLMs we investigated are misaligned with the values underpinning peer review, and suggest new research on aligning AI judgment systems with human goals in this context.

Original languageEnglish (US)
Title of host publicationCHI 2026 - Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems
EditorsNuria Oliver, David A. Shamma, Heloisa Candello, Pablo Cesar, Pedro Lopes, Alessandro Bozzon, Thomas Kosch, Vera Liao, Xiaojuan Ma, Valentino Artizzu, Fiona Draxler, Gustavo Lopez, Anke V. Reinschluessel, Xin Tong, Phoebe O. Toups Dugas
PublisherAssociation for Computing Machinery
ISBN (Electronic)9798400722783
DOIs
StatePublished - Apr 13 2026
Event2026 CHI Conference on Human Factors in Computing Systems, CHI 2026 - Barcelona, Spain
Duration: Apr 13 2026Apr 17 2026

Publication series

NameConference on Human Factors in Computing Systems - Proceedings

Conference

Conference2026 CHI Conference on Human Factors in Computing Systems, CHI 2026
Country/TerritorySpain
CityBarcelona
Period4/13/264/17/26

Keywords

  • Human Values
  • Large Language Models
  • Peer Review
  • Science

ASJC Scopus subject areas

  • Human-Computer Interaction
  • Computer Graphics and Computer-Aided Design
  • Software

Fingerprint

Dive into the research topics of 'All Accept, No Reject: Evaluating LLMs as "peer" Reviewers'. Together they form a unique fingerprint.

Cite this