arXiv cs.AI
· Papers
ReCBM: Uncertainty-Gated Relational Reasoning for Concept Bottleneck Models
arXiv:2608.10004v1 Announce Type: new Abstract: Concept Bottleneck Models (CBMs) provide an interpretable framework by grounding predictions in human-understandable concepts, enabling semantic inspection and test-time intervention. Recent variants have improved CBMs through richer concept representations, uncertainty e