PeerArg: Argumentative Peer Review with LLMs

TL;DR

This paper introduces PeerArg, a system combining large language models with knowledge representation to support and interpret peer review decisions, outperforming end-to-end LLM approaches.

Contribution

The paper presents a novel pipeline that integrates LLMs with knowledge representation to improve interpretability and accuracy in peer review prediction.

Findings

PeerArg outperforms end-to-end LLM in acceptance prediction

The system enhances interpretability of review analysis

Evaluation on three datasets demonstrates robustness

Abstract

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.