LLM在简历筛选中存在种族偏见？这篇研究揭示了AI招聘的公平性风险。
arXiv:2606.28978v1 Announce Type: new Abstract: We audit fourteen mainstream large language models (LLMs) for hiring discrimination using the paired-r…
最新研究量化了语音LLM中的交叉偏见，揭示声音特征与种族、性别等多重因素的交互影响，为AI公平性提供关键评估方法。
arXiv:2603.16941v2 Announce Type: replace-cross Abstract: Speech Large Language Models (SpeechLLMs) process spoken input directly, retaining cues such…
研究发现，多模态大模型的社会偏见主要源于少量人类视觉线索，而非文本信息，挑战传统认知。
arXiv:2606.20527v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are increasingly deployed in personally and societally conseq…
创新提出超越人口统计学的公平性优化方法，针对医学影像中基于外观的隐藏队列，提升模型性能与公平性。
arXiv:2605.29827v1 Announce Type: new Abstract: Medical image analysis models can exhibit performance disparities across patient subgroups, threatenin…
无需人口属性，也能实现人本AI的伦理公平性——论文提出在健康感知中消除偏见的新路径。
arXiv:2603.13373v3 Announce Type: replace-cross Abstract: In ubiquitous and mobile health systems, computational models infer human states from wearab…
AI聊天机器人存在宗教偏见，最新研究显示对天主教有偏爱倾向
Article URL: https://decrypt.co/369045/ai-chatbots-claude-chatgpt-bias-catholicism-pope-leo Comments URL: https://news.ycombinator.com/item?id=4828483…
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…
深度神经网络公平性修复新突破，提供可证明保证，已被ASE 2025录用。
arXiv:2605.19549v1 Announce Type: cross Abstract: Deep neural networks (DNNs) are suffering from ethical issues such as individual discrimination. In …