Research2026-04-28
Credal Concept Bottleneck Models for Epistemic-Aleatoric Uncertainty Decomposition
Source: Arxiv CS.AI
arXiv:2604.24170v1 Announce Type: new Abstract: Concept Bottleneck Models (CBMs) predict through human-interpretable concepts, but they typically output point concept probabilities that conflate epistemic uncertainty (reducible model underspecification) with aleatoric uncertainty (irreducible input...
arxivpapers