arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2510.12367cs.CLcs.AI
收藏

LLM-REVal:我们能否信任LLM审稿人?

LLM-REVal: Can We Trust LLM Reviewers Yet?

Peking University(北京大学);University of California, Los Angeles(加州大学洛杉矶分校);The Hong Kong Polytechnic University(香港理工大学);StepFun AI

Rui Li, Jia-Chen Gu, Po-Nien Kung, Heming Xia, Junfeng liu, Xiangwen Kong, Zhifang Sui, Nanyun Peng

AI总结:

本研究通过模拟研究智能体与评审智能体的互动,发现LLM审稿人存在系统性抬高LLM撰写论文分数、低估含批判性陈述的人类论文的偏见,但LLM评审指导的修订能提升论文质量,揭示了其在同行评审中的风险与潜力。

摘要:

大型语言模型(LLMs)的快速发展激励研究者将其广泛整合到学术工作流程中,这可能重塑研究实践和评审的方式。尽管先前的研究强调了LLMs在支持研究和同行评审方面的潜力,但它们在学术工作流程中的双重角色以及研究与评审之间的复杂互动带来了新的风险,这些风险在很大程度上尚未被充分探索。在本研究中,我们聚焦于LLMs深度整合到同行评审和研究过程中可能如何影响学术公平性,通过模拟来考察使用LLMs作为审稿人的潜在风险。该模拟包含一个研究智能体,它生成论文并进行修订,以及一个评审智能体,它评估提交的论文。基于模拟结果,我们进行人工标注,并识别出基于LLM的评审与人类判断之间的显著错位:(1)LLM审稿人系统性地抬高LLM撰写论文的分数,给予它们显著高于人类撰写论文的分数;(2)LLM审稿人持续低估带有批判性陈述(如风险、公平性)的人类撰写论文,即使经过多次修订也是如此。我们的分析揭示,这些现象源于LLM审稿人的两个主要偏见:偏向LLM生成写作风格的语言特征偏见,以及对批判性陈述的厌恶。这些结果凸显了如果在同行评审周期中不加足够谨慎地部署LLMs,对人类作者和学术研究所带来的风险和公平性问题。另一方面,由LLM评审指导的修订在基于LLM和人类评估中均带来质量提升,这说明了LLMs作为审稿人对早期研究者以及提升低质量论文的潜力。

英文摘要:

The rapid advancement of large language models (LLMs) has inspired researchers to integrate them extensively into the academic workflow, potentially reshaping how research is practiced and reviewed. While previous studies highlight the potential of LLMs in supporting research and peer review, their dual roles in the academic workflow and the complex interplay between research and review bring new risks that remain largely underexplored. In this study, we focus on how the deep integration of LLMs into both peer-review and research processes may influence scholarly fairness, examining the potential risks of using LLMs as reviewers by simulation. This simulation incorporates a research agent, which generates papers and revises, alongside a review agent, which assesses the submissions. Based on the simulation results, we conduct human annotations and identify pronounced misalignment between LLM-based reviews and human judgments: (1) LLM reviewers systematically inflate scores for LLM-authored papers, assigning them markedly higher scores than human-authored ones; (2) LLM reviewers persistently underrate human-authored papers with critical statements (e.g., risk, fairness), even after multiple revisions. Our analysis reveals that these stem from two primary biases in LLM reviewers: a linguistic feature bias favoring LLM-generated writing styles, and an aversion toward critical statements. These results highlight the risks and equity concerns posed to human authors and academic research if LLMs are deployed in the peer review cycle without adequate caution. On the other hand, revisions guided by LLM reviews yield quality gains in both LLM-based and human evaluations, illustrating the potential of the LLMs-as-reviewers for early-stage researchers and enhancing low-quality papers.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑