研究人员引入了就地交互审计（SIA），一个旨在通过关注用户特征如何影响模型响应来识别大型语言模型（LLM）中偏见的新框架。与之前审计LLM如何表征外部群体的旧方法不同，SIA检查用户内隐或声明的身份如何影响LLM输出的质量、内容和语气。这种以用户为中心的方法旨在揭示在用户与模型直接交互中表现出的偏见，为自然语言处理（NLP）研究开辟了新方向。 AI
影响 该框架可以通过关注用户特定的交互而非普遍的群体表征，从而更细致地检测LLM偏见。
排序理由 该集群包含一篇详细介绍LLM偏见审计新研究框架的学术论文。
AI 生成摘要 · Google Gemini · 来自 2 个来源。 我们如何撰写摘要 →
arXiv:2606.12247v1 Announce Type: cross Abstract: Research on bias in large language models (LLMs) has predominantly focused on third-person audits, which study how models represent or evaluate demographic groups as external subjects. However, this paradigm overlooks a structural…
Research on bias in large language models (LLMs) has predominantly focused on third-person audits, which study how models represent or evaluate demographic groups as external subjects. However, this paradigm overlooks a structural blind spot because the user is absent from the au…