PeerArg: Argumentative Peer Review with LLMs
This addresses the need for more interpretable and trustworthy peer review support in scientific publishing, though it appears incremental as it builds on existing NLP techniques.
The paper tackles the problem of subjective and biased peer review by proposing PeerArg, a pipeline combining LLMs with knowledge representation to predict paper acceptance from reviews, and shows that a variant of PeerArg outperforms an end-to-end LLM baseline.
Peer review is an essential process to determine the quality of papers submitted to scientific conferences or journals. However, it is subjective and prone to biases. Several studies have been conducted to apply techniques from NLP to support peer review, but they are based on black-box techniques and their outputs are difficult to interpret and trust. In this paper, we propose a novel pipeline to support and understand the reviewing and decision-making processes of peer review: the PeerArg system combining LLMs with methods from knowledge representation. PeerArg takes in input a set of reviews for a paper and outputs the paper acceptance prediction. We evaluate the performance of the PeerArg pipeline on three different datasets, in comparison with a novel end-2-end LLM that uses few-shot learning to predict paper acceptance given reviews. The results indicate that the end-2-end LLM is capable of predicting paper acceptance from reviews, but a variant of the PeerArg pipeline outperforms this LLM.