AI RESEARCH
Rethinking Concept Bottleneck Models: From Pitfalls to Solutions
arXiv CS.CV
•
ArXi:2603.05629v1 Announce Type: new Concept Bottleneck Models (CBMs) ground predictions in human-understandable concepts but face fundamental limitations: the absence of a metric to pre-evaluate concept relevance, the "linearity problem" causing recent CBMs to bypass the concept bottleneck entirely, an accuracy gap compared to opaque models, and finally the lack of systematic study on the impact of different visual backbones and VLMs. We