1
Auditing of Unlearning Algorithms
聚焦机器学习遗忘算法的可信度审计，探讨如何验证模型真正删除用户数据，关乎隐私合规与AI治理。
arXiv:2607.05898v1 Announce Type: new Abstract: Evaluating whether unlearning algorithms truly remove training data influence remains an open challeng…
2
Whose fairness? Structural concentration in AI bias research
从结构视角拆解AI偏差研究，追问公平性定义与基准背后的权力集中和盲点。
arXiv:2607.05574v1 Announce Type: cross Abstract: Artificial intelligence increasingly mediates consequential decisions in healthcare, law, and public…
3
Whose hotel does the AI recommend? An algorithm audit of reputation signals in LLM-assisted hotel selection
大模型推荐酒店时更偏爱哪些声誉信号？这篇算法审计研究揭示AI作为信息守门人的偏见。
arXiv:2606.16344v1 Announce Type: new Abstract: Travelers increasingly ask large language model (LLM) assistants which hotel to book, making these sys…
4
Anchoring LLM Gender Bias to Human Baselines: A Cross-Lingual Audit
跨语言审计揭示大模型性别偏见与人类基线差异，公平性研究新视角
arXiv:2605.30804v1 Announce Type: new Abstract: We audit six large language models (LLMs) for gender stereotyping across English, Korean, Chinese, and…