Concept Bottleneck Models (CBMs) built on vision-language models such as CLIP represent a latent space as human-understandable concepts. These representations are unfaithful: related concepts are enta...
arXiv:2606. 30498v1 Announce Type: cross Abstract: Human decision-making interprets the world through high-level concepts, such as recognizing a bird by its belly color.
arXiv:2606. 04326v1 Announce Type: cross Abstract: Concept bottleneck models predict outcomes from high-level concepts detected in inputs.
arXiv:2609.38625v1 Announce Type: cross Abstract: Concept Bottleneck Models (CBMs) are designed to provide interpretable intermediate representations, yet how such bottlenecks affect robustness remai...
arXiv:2602. 02886v3 Announce Type: replace-cross Abstract: Concept Bottleneck Models (CBMs) promote interpretability by grounding predictions in human-understandable concepts.
arXiv:2601. 21944v3 Announce Type: replace Abstract: The widespread adoption of deep learning models in computer vision has intensified concerns about interpretability.
Concept bottleneck models predict outcomes from high-level concepts detected in inputs. Although concepts provide a simple way to reap benefits from interpretability, very few datasets include concept labels.
arXiv:2510. 15770v4 Announce Type: replace-cross Abstract: Although deep neural networks achieve strong predictive performance, their internal reasoning often remains difficult to inspect and control.
arXiv:2606. 26155v1 Announce Type: new Abstract: Interpreting and controlling model behaviors through activation steering methods requires many pairs of contrastive samples that clearly exhibit desired or undesired behavior.
arXiv:2606. 19489v1 Announce Type: cross Abstract: Concept Bottleneck Models (CBMs) enhance interpretability by projecting learned features into a human-understandable concept space.
arXiv:2606. 00082v1 Announce Type: cross Abstract: Explainability of deep learning algorithms is critical for computer-vision applications with high-stake decisions.
arXiv:2506. 20040v3 Announce Type: replace-cross Abstract: Interpreting language models remains challenging due to the existence of residual stream, which linearly mixes and duplicates features across adjacent layers, causing single-layer analyses to miss this cross-layer structure.