用大模型辅助培养评审人，解决学术评审质量下降问题
Position on LLM-Assisted Peer Review: Addressing Reviewer Gap through Mentoring and Feedback
- 让大模型充当评审人导师，长期提升评审能力
- 提供即时反馈，帮助评审人改进当前评阅质量
- 适合希望提升评审水平的研究者和期刊编辑
AI研究的快速扩张加剧了评审人短缺问题，威胁同行评审的可持续性，并导致低质量评审的恶性循环。本文批判现有通过大模型自动生成评审意见的方法，主张将大模型定位为辅助和教育人类评审人的工具。我们提出高质量评审的核心原则，并设计两个互补系统：(i) 大模型辅助的导师系统，用于长期培养评审人能力；(ii) 大模型辅助的反馈系统，帮助评审人优化评审质量。这一以人为本的范式旨在增强评审专业能力，推动构建更可持续的学术生态。
原文摘要 · Abstract (English)
The rapid expansion of AI research has intensified the Reviewer Gap, threatening the peer-review sustainability and perpetuating a cycle of low-quality evaluations. This position paper critiques existing LLM approaches that automatically generate reviews and argues for a paradigm shift that positions LLMs as tools for assisting and educating human reviewers. We define the core principles of high-quality peer review and propose two complementary systems grounded in these foundations: (i) an LLM-assisted mentoring system that cultivates reviewers' long-term competencies, and (ii) an LLM-assisted feedback system that helps reviewers refine the quality of their reviews. This human-centered approach aims to strengthen reviewer expertise and contribute to building a more sustainable scholarly ecosystem.
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。