Justice in Judgment: Unveiling (Hidden) Bias in LLM-assisted Peer Reviews
This addresses fairness concerns in automated peer review systems, which is crucial for researchers and academic publishers, though it is incremental as it documents known risks rather than proposing solutions.
The paper investigated bias in LLM-generated peer reviews through controlled experiments on sensitive metadata like author affiliation and gender, finding consistent affiliation bias favoring highly-ranked institutions and subtle gender preferences that could compound over time.
The adoption of large language models (LLMs) is transforming the peer review process, from assisting reviewers in writing more detailed evaluations to generating entire reviews automatically. While these capabilities offer exciting opportunities, they also raise critical concerns about fairness and reliability. In this paper, we investigate bias in LLM-generated peer reviews by conducting controlled experiments on sensitive metadata, including author affiliation and gender. Our analysis consistently shows affiliation bias favoring institutions highly ranked on common academic rankings. Additionally, we find some gender preferences, which, even though subtle in magnitude, have the potential to compound over time. Notably, we uncover implicit biases that become more evident with token-based soft ratings.