1
The Impossibility of Eliciting Latent Knowledge
论文证明无法可靠提取AI模型的潜在知识，为AI安全与可解释性带来理论限制。
arXiv:2606.12268v1 Announce Type: new Abstract: Advanced AI systems have extensive knowledge of their environments; in fact, their knowledge may (far)…
2
The Attribution Impossibility: No Feature Ranking Is Faithful, Stable, and Complete Under Collinearity
这项研究证明了在共线性条件下，任何特征排名都无法同时满足忠实性、稳定性和完备性，对机器学习可解释性理论有重要影响。
arXiv:2605.21492v1 Announce Type: cross Abstract: No feature ranking can be simultaneously faithful, stable, and complete when features are collinear.…