RubricReviewer：从直接批评到客观全面的评分标准驱动同行评审
原标题：RubricReviewer: From Direct Critique to Objective and Comprehensive Rubric-Driven Peer Review
AI 摘要
RubricReviewer是一个全新的同行评审框架，通过将评分标准生成作为显式中间步骤，并融合无训练代理（Scout）与人类对齐训练模型（Aligner），解决了现有LLM评审员的两大结构性局限。实验表明，该框架生成的评审比现有系统更全面、更具区分度，且对对抗性提示注入攻击的鲁棒性最强。消融研究证实了每个组件的必要性。
正文节选
Computer Science > Computation and Language Title:RubricReviewer: From Direct Critique to Objective and Comprehensive Rubric-Driven Peer Review View PDF HTML (experimental) Abstract:Peer review at major venues is under unprecedented submission pressure, motivating the use of large language models (LLMs) as review assistants. Existing LLM-based reviewers, however, face two structural limitations. First, they map manuscripts directly to reviews, leaving the underlying rubric implicit a