AI能否成为合格的同行评审员？这篇综述系统梳理了全流程自动化方案。
Can AI Be a Good Peer Reviewer? A Survey of Peer Review Process, Evaluation, and the Future
- 提出生成、回应、元评审等环节的AI实现方法
- 对比多种评估方式，涵盖人类、基准与大模型评价
- 适合研究AI辅助学术出版的学者和期刊编辑
同行评审是包含审稿、辩驳、元评审、最终决定及后续修改的多阶段流程。近年来大语言模型（LLMs）的发展推动了该流程中不同阶段的辅助或自动化方法。本文综述了三类技术：(i) 审稿生成，包括微调策略、基于代理的系统、强化学习方法及新兴范式；(ii) 审稿后任务，如辩驳、元评审与根据审稿意见修订稿件；(iii) 评估方法，涵盖以人类为中心、基于参考标准、基于大模型和面向特定维度的评估。文章整理了相关数据集，比较建模选择，讨论局限性、伦理问题与未来方向。旨在为构建、评估和集成全链条大模型系统提供实用指导。
原文摘要 · Abstract (English)
Peer review is a multi-stage process involving reviews, rebuttals, meta-reviews, final decisions, and subsequent manuscript revisions. Recent advances in large language models (LLMs) have motivated methods that assist or automate different stages of this pipeline. In this survey, we synthesize techniques for (i) peer review generation, including fine-tuning strategies, agent-based systems, RL-based methods, and emerging paradigms to enhance generation; (ii) after-review tasks including rebuttals, meta-review and revision aligned to reviews; and (iii) evaluation methods spanning human-centered, reference-based, LLM-based and aspect-oriented. We catalog datasets, compare modeling choices, and discuss limitations, ethical concerns, and future directions. The survey aims to provide practical guidance for building, evaluating, and integrating LLM systems across the full peer review workflow.
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。