AutoRev: Multi-Modal Graph Retrieval for Automated Peer-Review Generation
This addresses the challenge of improving efficiency and quality in academic publishing for authors and reviewers, though it appears incremental as it builds on existing retrieval-augmented generation methods.
The paper tackled the problem of automating peer-review generation by proposing AutoRev, a system that uses a multi-modal graph retrieval framework to enhance feedback quality, achieving up to 58.72% improvement over baselines and competitive human evaluation results.
Enhancing the quality and efficiency of academic publishing is critical for both authors and reviewers, as research papers are central to scholarly communication and a major source of high-quality content on the web. To support this goal, we propose AutoRev, an automatic peer-review system designed to provide actionable, high-quality feedback to both reviewers and authors. AutoRev leverages a novel Multi-Modal Retrieval-Augmented Generation (RAG) framework that combines textual and graphical representations of academic papers. By modelling documents as graphs, AutoRev effectively retrieves the most pertinent information, significantly reducing the input context length for LLMs and thereby enhancing their review generation capabilities. Experimental results show that AutoRev outperforms state-of-the-art baselines by up to 58.72% and demonstrates competitive performance in human evaluations against ground truth reviews. We envision AutoRev as a powerful tool to streamline the peer-review workflow, alleviating challenges and enabling scalable, high-quality scholarly publishing. By guiding both authors and reviewers, AutoRev has the potential to accelerate the dissemination of quality research on the web at a larger scale. Code will be released upon acceptance.