arXiv cs.CV
· Papers
Concept Labels Are Not Enough: Rethinking Concept Bottleneck Models through Representation Integrity
arXiv:2510.15770v4 Announce Type: replace Abstract: Although deep neural networks achieve strong predictive performance, their internal reasoning often remains difficult to inspect and control. Concept Bottleneck Models (CBMs) address this opacity by factoring predictions through human-understandable concepts, thereby