Abstract:Scientific paper evaluation often involves not only assessing a manuscript itself, but also relating it to contemporaneous research and prior literature. However, existing LLM-based methods typically model these signals separately and lack a unified mechanism for propagating review evidence across papers. We propose $\textbf{GraphReview}$, a graph-based LLM framework that formulates paper evaluation as review-signal message passing over a semantic paper graph. The graph jointly captures intrinsic quality, synchronic links among contemporaneous papers, and diachronic links to prior work. LLMs are used to estimate node-level quality priors and generate edge-level comparative evidence through pairwise paper comparisons, while Personalized PageRank integrates review signals for quality ranking, decision prediction, and review generation. To produce higher-quality graph evidence, we propose reward-induced maximum likelihood objectives for training the LLM backbones. Experiments show that GraphReview consistently outperforms the strongest baseline, achieving average improvements of 29.7% on decision and ranking metrics, including gains of 23.7% in Accuracy and 57.6% in Spearman's $\rho$. It also produces higher-quality review texts and generalizes effectively across time periods and conference venues. The code is available at this https URL.
| Subjects: | Computation and Language (cs.CL); Information Retrieval (cs.IR) |
| Cite as: | arXiv:2605.27204 [cs.CL] |
| (or arXiv:2605.27204v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2605.27204 arXiv-issued DOI via DataCite (pending registration) |
From: Pujun Zheng [view email]
[v1]
Tue, 26 May 2026 15:58:49 UTC (4,747 KB)
此内容由惯性聚合(RSS阅读器)自动聚合整理，仅供阅读参考。 原文来自 — 版权归原作者所有。