AgentReview: Exploring Peer Review Dynamics with LLM Agents
This study provides insights to improve peer review mechanisms for scientific publication, though it is incremental in applying LLMs to simulate a known process.
The paper tackled the problem of analyzing peer review dynamics by developing AgentReview, an LLM-based simulation framework that disentangles latent factors and addresses privacy issues, revealing a 37.1% variation in paper decisions due to reviewer biases.
Peer review is fundamental to the integrity and advancement of scientific publication. Traditional methods of peer review analyses often rely on exploration and statistics of existing peer review data, which do not adequately address the multivariate nature of the process, account for the latent variables, and are further constrained by privacy concerns due to the sensitive nature of the data. We introduce AgentReview, the first large language model (LLM) based peer review simulation framework, which effectively disentangles the impacts of multiple latent factors and addresses the privacy issue. Our study reveals significant insights, including a notable 37.1% variation in paper decisions due to reviewers' biases, supported by sociological theories such as the social influence theory, altruism fatigue, and authority bias. We believe that this study could offer valuable insights to improve the design of peer review mechanisms. Our code is available at https://github.com/Ahren09/AgentReview.