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 2510.01255cs.CLcs.CYcs.HC
收藏

大语言模型对社会议题内容审核的纵向监测

Longitudinal Monitoring of LLM Content Moderation of Social Issues

Yunlang Dai, Emma Lurie, Danaé Metaxa, Sorelle A. Friedler

AI总结:

针对大语言模型内容审核政策不透明且多变的问题,提出纵向审计系统AI Watchman,通过400余个社会议题数据集审计多款模型,可检测未公开的政策变化、识别审核差异并分类拒绝形式,为LLM纵向审计提供工具与实证。

摘要:

大语言模型(LLM)的输出由不透明且频繁变动的企业内容审核政策与实践塑造。LLM的审核通常以拒绝的形式呈现;模型拒绝生成特定主题的文本,既反映了企业政策,也潜移默化地影响着公共话语。我们提出AI Watchman(人工智能监督员),这是一套纵向审计系统,用于公开测量和追踪LLM随时间变化的拒绝行为,为LLM这一重要的黑箱环节提供透明度。我们基于包含400余个社会议题的数据集,审计了OpenAI的审核端点、GPT-4.1、GPT-5以及DeepSeek(涵盖英文和中文两种语言)。研究发现,AI Watchman能够检测到企业政策的变化,即便这些变化未公开宣布;同时我们还识别出不同企业、不同模型在内容审核上的差异。我们也对不同形式的拒绝行为进行了定性分析与分类。本研究为LLM纵向审计的价值提供了实证依据,而AI Watchman正是开展此类审计的一套系统。

英文摘要:

Large language models' (LLMs') outputs are shaped by opaque and frequently-changing company content moderation policies and practices. LLM moderation often takes the form of refusal; models' refusal to produce text about certain topics both reflects company policy and subtly shapes public discourse. We introduce AI Watchman, a longitudinal auditing system to publicly measure and track LLM refusals over time, to provide transparency into an important and black-box aspect of LLMs. Using a dataset of over 400 social issues, we audit Open AI's moderation endpoint, GPT-4.1, and GPT-5, and DeepSeek (both in English and Chinese). We find evidence that changes in company policies, even those not publicly announced, can be detected by AI Watchman, and identify company- and model-specific differences in content moderation. We also qualitatively analyze and categorize different forms of refusal. This work contributes evidence for the value of longitudinal auditing of LLMs, and AI Watchman, one system for doing so.

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。

↑