用大模型模拟审稿人作者辩论，构建图结构提升论文评审准确性
Automatic Paper Reviewing with Heterogeneous Graph Reasoning over LLM-Simulated Reviewer-Author Debates
- 通过大模型模拟多轮审稿辩论，构建包含意见关系的异构图
- 在三个数据集上平均比基线提升15.73%，更准确捕捉论证过程
- 适合需要可解释评审决策的研究者和会议投稿系统
现有论文评审方法常依赖表面文本特征或直接使用大语言模型（LLMs），易产生幻觉、评分偏见且推理能力有限。此外，这些方法难以捕捉审稿人与作者互动中的复杂论证与协商动态。为此，我们提出ReViewGraph（审稿人-作者辩论图推理器），一种基于大模型模拟多轮审稿-作者辩论的异构图推理框架。通过大模型多智能体协作模拟审稿互动，将接受、拒绝、澄清、妥协等多样意见关系显式提取并编码为异构图中的类型边。利用图神经网络对结构化辩论图进行推理，ReViewGraph能捕获细粒度论证动态，实现更可靠的评审决策。在三个数据集上的大量实验表明，ReViewGraph相比强基线平均相对提升15.73%，验证了建模详细审稿辩论结构的价值。
原文摘要 · Abstract (English)
Existing paper review methods often rely on superficial manuscript features or directly on large language models (LLMs), which are prone to hallucinations, biased scoring, and limited reasoning capabilities. Moreover, these methods often fail to capture the complex argumentative reasoning and negotiation dynamics inherent in reviewer-author interactions. To address these limitations, we propose ReViewGraph (Reviewer-Author Debates Graph Reasoner), a novel framework that performs heterogeneous graph reasoning over LLM-simulated multi-round reviewer-author debates. In our approach, reviewer-author exchanges are simulated through LLM-based multi-agent collaboration. Diverse opinion relations (e.g., acceptance, rejection, clarification, and compromise) are then explicitly extracted and encoded as typed edges within a heterogeneous interaction graph. By applying graph neural networks to reason over these structured debate graphs, ReViewGraph captures fine-grained argumentative dynamics and enables more informed review decisions. Extensive experiments on three datasets demonstrate that ReViewGraph outperforms strong baselines with an average relative improvement of 15.73%, underscoring the value of modeling detailed reviewer-author debate structures.
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。