Graph-Guided Passage Retrieval for Author-Centric Structured Feedback

TL;DR

AutoRev is an automated system that uses graph-based retrieval and generation to provide structured, actionable feedback on academic papers before peer review, improving quality and efficiency.

Contribution

It introduces a novel graph-guided retrieval-augmented generation framework for author-centric feedback, reducing input length and enhancing feedback quality.

Findings

AutoRev outperforms baseline methods on automatic metrics.

AutoRev achieves strong results in human evaluations.

The system effectively models paper structure for better retrieval.

Abstract

Obtaining high-quality, pre-submission feedback is a critical bottleneck in the academic publication lifecycle for researchers. We introduce AutoRev, an automated author-centric feedback system that generates structured, actionable guidance prior to formal peer review. AutoRev employs a graph-based retrieval-augmented generation framework that models each paper as a hierarchical document graph, integrating textual and structural representations to retrieve salient content efficiently. By leveraging graph-based passage retrieval, AutoRev substantially reduces LLM input context length, leading to higher-quality feedback generation. Experimental results demonstrate that AutoRev significantly outperforms baselines across multiple automatic evaluation metrics, while achieving strong performance in human evaluations. Code will be released upon acceptance.