AI在宗教信仰转换建议上表现出系统性偏见，研究揭示大模型对特定宗教的隐性偏向
arXiv:2605.22975v1 Announce Type: new Abstract: We ask whether large language models (LLMs) treat queries about religious conversion symmetrically. Th…
研究发现大模型地缘政治偏见来自后训练而非数据，提示语言会放大偏见，颠覆传统认知。
arXiv:2605.23825v1 Announce Type: cross Abstract: It has generally been assumed that geopolitical bias in language models originates from the training…
大语言模型作为自动评估者，会被对话历史中的观点极性所影响，一项覆盖7.5万样本的研究揭示了这种“累积消息效应”
arXiv:2605.22714v1 Announce Type: cross Abstract: Large language models are routinely used as automated evaluators: to review code, moderate content, …
当老板和员工都用AI润色邮件，一场沟通灾难悄然上演——LLM引导下的解读偏差正在制造职场"死亡螺旋"。
Over the last year and a half I have witnessed something that is truly alarming. I am calling it "The LLM Death Spiral". This is the case of two peopl…
从机制层面揭示链式思考提示如何放大或缓解LLM中的性别偏见，ICLR 2026 Workshop前沿研究。
arXiv:2605.20410v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in socially sensitive settings despite substant…
最新研究揭示LLM中两类微妙偏见——刻板印象与偏离，量化评估方法出炉
arXiv:2508.06649v3 Announce Type: replace Abstract: Large language models (LLMs) are widely applied across diverse domains, raising concerns about the…
临床文档里的污名化语言，会如何悄悄带偏大模型的医疗决策？这篇论文揭秘偏见机制
arXiv:2605.17228v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in high-stakes domains such as clinical decisio…
大模型同质化如何威胁AI安全？这篇论文系统剖析了症结与出路。
arXiv:2601.06116v5 Announce Type: replace-cross Abstract: Generative AI models reproduce the human biases in their training data and further amplify t…
ContraPoints用轨道激光炮般的论证，炸毁关于偏见的懒散言论，看完秒变聪明。
This is a fabulous video by ContraPoints about J.K. Rowling, anti-trans sentiments, and what bigotry really is . I love Natalie’s videos for so many r…
揭示大模型英语偏见真相，证明持续预训练成本优势不存在，语言专用投资或成必然。
arXiv:2605.15613v1 Announce Type: new Abstract: Through an analysis of sequences generated by open-weight large language models (LLMs), we demonstrate…
探讨机器学习系统中利益冲突导致的偏见问题，提出当前解决方案的局限性。
arXiv:2605.15504v1 Announce Type: cross Abstract: Financial, social, and political factors often prevent the interests of the owners of ML systems and…
突破传统结果公平，提出GESD度量过程解释稳定性，揭示算法偏见新维度
arXiv:2605.15295v1 Announce Type: cross Abstract: Machine learning (ML) algorithms are increasingly deployed in high-stakes decision-making domains su…