Clarity: The Flexibility-Interpretability Trade-Off in Sparsity-aware Concept Bottleneck Models

ArXi:2601.21944v2 Announce Type: replace The widespread adoption of deep learning models in computer vision has intensified concerns about interpretability. Despite strong performance, these models are often treated as black boxes, with limited systematic investigation of their decision-making processes. While many interpretability methods exist, objective evaluation of learned representations remains limited, particularly for approaches that rely on sparsity to "induce" interpretability.