通过编码任务揭示大语言模型在高风险决策中的潜在偏见，创新评估方法值得关注
arXiv:2501.05396v3 Announce Type: replace Abstract: Large language models (LLMs) are increasingly used in high-stakes decisions such as hiring and col…
最新研究揭露顶级大模型在处理盲文时的严重无障碍缺陷，值得开发者与残障社区关注。
arXiv:2607.11893v1 Announce Type: new Abstract: Large Language Models (LLMs) perform strongly on many language tasks, but their capability in structur…
用机械可解释性方法解剖LLM作为评判者时的内在偏见，揭示不公平机制根源
arXiv:2607.11871v1 Announce Type: cross Abstract: Existing studies of LLM-as-judge scoring bias work predominantly at the input-output level: they per…
自适应生成问题来精准挖掘LLM潜在偏见，为AI安全提供全新检测方案
arXiv:2510.12857v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are now widely deployed in user-facing applications, reaching h…
研究医疗大模型问答中的不公平现象，揭示不同人群间的表现差异。
arXiv:2510.17476v2 Announce Type: replace Abstract: Equitable access to reliable health information is vital when integrating AI into healthcare. Yet,…
用逻辑网格谜题精准探测大模型推理中的隐性偏见，一场理性与偏好的博弈实验
arXiv:2511.06160v2 Announce Type: replace Abstract: While recent safety guardrails effectively suppress overtly biased outputs, subtler forms of socia…
用“选7”小游戏揭示LLM缺乏真正随机性，一家初创公司正破解这种AI群体思维困局。
Let’s start with a game. Open up your chatbot of choice—Claude, ChatGPT, Gemini—and type “Give me a random number between 1 and 10.” You’re going to g…
新方法RoPoLL让LLM评判者更鲁棒，18倍参数优势却更精准，有效对抗偏见污染。
arXiv:2606.30931v1 Announce Type: new Abstract: The LLM Jury, a Panel of LLM Evaluators (PoLL) reporting consensus scores, has become a practical alte…
复现FACTER公平性方法，用共形阈值和提示修复降低AI偏见，新鲜视角值得关注。
arXiv:2606.28620v1 Announce Type: cross Abstract: Fayyazi et al. (2025) recently proposed FACTER, a model-agnostic framework designed to jointly enfor…
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…
AI代理被称为「同事」比叫聊天机器人更能提升错误察觉率，命名影响信任与效率。
This story originally appeared in The Algorithm, our weekly newsletter on AI. To get stories like this in your inbox first, sign up here. Imagine comi…
AI编码代理在依赖选择上已有明显偏好，开发者需警惕其对决策的无声影响。
Deep into a coding session, you realize you want beta testers to try some new functionality first. You ask your agent to add feature flagging to your …
系统评估LLM作为裁判时的偏见缓解策略，揭示不同方法的有效性，为构建公平AI评估体系提供关键指南。
arXiv:2604.23178v2 Announce Type: replace Abstract: LLM-as-a-Judge has become the dominant paradigm for evaluating language model outputs, yet LLM jud…
六大主流大模型政治立场大揭秘，左倾明显，还有互动测试帮你找到最接近的模型
Article URL: https://trakkr.ai/bias Comments URL: https://news.ycombinator.com/item?id=48672779 Points: 4 # Comments: 5
一键查看Ian Bremmer关于AI聊天机器人政治偏见的推文，快速了解AI伦理争议的核心观点。
Article URL: https://twitter.com/ianbremmer/status/2069744192230764723 Comments URL: https://news.ycombinator.com/item?id=48664533 Points: 7 # Comment…
揭秘LLM安全评估的致命缺陷：看似全面防护实则暗藏针对特定群体的盲区，戳破“选择性安全陷阱”系统性风险
arXiv:2601.04389v3 Announce Type: replace-cross Abstract: Current safety evaluations of large language models (LLMs) create a dangerous illusion of un…
多模态大模型当评委也有偏见？论文揭示文化模糊下校准失败的关键漏洞。
arXiv:2606.20676v1 Announce Type: cross Abstract: MLLM-as-a-Judge is conventionally validated by agreement with human annotations, but this metric is …
LLM agent 记忆系统竟会传播评估偏见，揭示偏见在时间维度上的跨际扩散机制，值得关注。
arXiv:2606.23195v1 Announce Type: cross Abstract: Large Language Model (LLM) agents increasingly rely on memory systems to maintain long-term coherenc…
让大模型避免框架效应影响，从隐藏偏见走向真正公平
arXiv:2602.04306v2 Announce Type: replace-cross Abstract: As large language models (LLMs) are increasingly deployed in real-world applications, ensuri…
用随机路径聚合可视化LLM生成中的隐藏偏见，揭秘文本背后的系统性偏差。
arXiv:2606.19344v1 Announce Type: cross Abstract: Large Language Models (LLMs) exhibit representational and syntactic biases that are difficult to eva…