Abstract Concept Bottleneck Models (CBMs) tackle the opacity of neural architectures by
constructing and explaining their predictions using a set of high-level concepts. A special …

Human feedback plays a critical role in learning and refining reward models for text-to-
image generation, but the optimal form the feedback should take for learning an accurate …

Model explanations can be valuable for interpreting and debugging predictive models. We
study a specific kind called Concept Explanations, where the goal is to interpret a model …

Abstract Concept-based methods have emerged as a promising direction to develop
interpretable neural networks in standard supervised settings. However, most works that …