用图结构统一整合论文质量与文献关联，提升学术评价准确性
GraphReview: Scientific Paper Evaluation via LLM-based Graph Evidence Expansion
- 构建论文语义图，融合内在质量与跨时空引用关系
- 对比分析论文对，生成可解释的评审证据，准确率提升23.7%
- 支持跨会议、跨时段泛化，适合科研评估与审稿辅助
科学论文评估不仅需审视稿件本身，还需关联同期研究与既有文献。现有基于大模型的方法通常分步处理这些信号，缺乏统一的证据聚合机制。我们提出GraphReview，一种基于图结构的LLM框架，将论文评估建模为推理阶段的语义论文图证据扩展。该图联合捕捉论文内在质量、同期论文间的同步关联及与历史工作的历时关联。利用LLM估计节点级质量先验，并通过论文对比较生成边级对比证据；个性化PageRank整合这些结构化信号，实现质量排序、决策预测与评审文本生成。为提升图证据质量，我们设计了基于奖励的极大似然训练目标。实验表明，GraphReview持续优于最强基线，在决策与排序指标上平均提升29.7%，包括准确率提升23.7%和斯皮尔曼相关系数ρ提升57.6%。其生成的评审文本质量更高，且在不同时间段与会议场景下具有良好泛化能力。
原文摘要 · Abstract (English)
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 aggregating review evidence across papers. We propose $\textbf{GraphReview}$, a graph-based LLM framework that formulates paper evaluation as inference-time graph evidence expansion 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 these structured 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 $ρ$. It also produces higher-quality review texts and generalizes effectively across time periods and conference venues.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。