别让表面效度骗了你——FAccT新方法教你证伪预测算法的判别效度，直击AI验证中的隐蔽陷阱
arXiv:2601.17146v2 Announce Type: replace-cross Abstract: Empirical investigations into unintended model behavior often show that the algorithm is pre…
提出验证方法与开放世界基准，提升模型忠实性的可解释AI研究
arXiv:2605.27879v1 Announce Type: new Abstract: Explainable AI (XAI) helps users interpret model behavior and identify potential faults. Agentic XAI s…
扩散大模型幻觉检测新方法：利用隐藏证据验证，捕捉生成轨迹中的幻觉信号，突破传统输出检测局限。
arXiv:2604.26139v2 Announce Type: replace Abstract: Diffusion large language models generate text through multi-step denoising, where hallucination si…