arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2403.07183cs.CLcs.AIcs.LGcs.SI
收藏

大规模监控AI修改内容:ChatGPT对AI会议同行评审影响的案例研究

Monitoring AI-Modified Content at Scale: A Case Study on the Impact of ChatGPT on AI Conference Peer Reviews

Department of Computer Science, Stanford University(斯坦福大学计算机科学系);Machine Learning Department, NEC Labs America(NEC美国实验室机器学习部门);Department of Biomedical Data Science, Stanford University(斯坦福大学生物医学数据科学系);Department of Electrical Engineering, Stanford University(斯坦福大学电气工程系);Graduate School of Education, Stanford University(斯坦福大学教育研究生院);Department of Sociology, Stanford University(斯坦福大学社会学系);Graduate School of Business, Stanford University(斯坦福大学商学院);Department of Management Science and Engineering, Stanford University(斯坦福大学管理科学与工程系);Department of Computer Science, UC Santa Barbara(加州大学圣芭芭拉分校计算机科学系)

Weixin Liang, Zachary Izzo, Yaohui Zhang, Haley Lepp, Hancheng Cao, Xuandong Zhao, Lingjiao Chen, Haotian Ye, Sheng Liu, Zhi Huang, Daniel A. McFarland, James Y. Zou

AI总结:

本文提出了一种方法,用于估计大规模语料库中可能被大语言模型(LLM)显著修改或生成的文本比例。通过专家撰写和AI生成的参考文本,该最大似然模型能够高效地在语料库层面考察实际的LLM使用情况。研究以ChatGPT发布后举行的AI会议同行评审(ICLR 2024、NeurIPS 2023、CoRL 2023和EMNLP 2023)为案例,发现6.5%至16.9%的提交文本可能被LLM显著修改。生成文本的情境揭示了用户行为:在信心较低、接近截止日期或回复作者反驳较少的评审中,估计的LLM生成文本比例更高。此外,观察到语料库层面的趋势可能过于微妙,无法在个体层面检测到,并讨论了这些趋势对同行评审的影响。呼吁未来跨学科研究探讨LLM使用如何改变我们的信息和知识实践。

摘要:

我们提出了一种方法,用于估计大规模语料库中可能被大语言模型(LLM)显著修改或生成的文本比例。我们的最大似然模型利用专家撰写和AI生成的参考文本,以准确且高效的方式在语料库层面考察实际的LLM使用情况。我们将该方法应用于ChatGPT发布后举行的AI会议同行评审案例研究,包括ICLR 2024、NeurIPS 2023、CoRL 2023和EMNLP 2023。我们的结果表明,在这些会议中提交的同行评审文本中,6.5%至16.9%可能被LLM显著修改,即超出拼写检查或小幅写作更新的范围。生成文本出现的情境提供了关于用户行为的见解:估计的LLM生成文本比例在信心较低、接近截止日期或来自较少回应作者反驳的评审中更高。我们还观察到语料库层面的生成文本趋势,这些趋势可能在个体层面过于微妙而无法检测到,并讨论了这些趋势对同行评审的影响。我们呼吁未来跨学科研究探讨LLM使用如何改变我们的信息和知识实践。

英文摘要:

We present an approach for estimating the fraction of text in a large corpus which is likely to be substantially modified or produced by a large language model (LLM). Our maximum likelihood model leverages expert-written and AI-generated reference texts to accurately and efficiently examine real-world LLM-use at the corpus level. We apply this approach to a case study of scientific peer review in AI conferences that took place after the release of ChatGPT: ICLR 2024, NeurIPS 2023, CoRL 2023 and EMNLP 2023. Our results suggest that between 6.5% and 16.9% of text submitted as peer reviews to these conferences could have been substantially modified by LLMs, i.e. beyond spell-checking or minor writing updates. The circumstances in which generated text occurs offer insight into user behavior: the estimated fraction of LLM-generated text is higher in reviews which report lower confidence, were submitted close to the deadline, and from reviewers who are less likely to respond to author rebuttals. We also observe corpus-level trends in generated text which may be too subtle to detect at the individual level, and discuss the implications of such trends on peer review. We call for future interdisciplinary work to examine how LLM use is changing our information and knowledge practices.

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。

↑