SL-CBM: Enhancing Concept Bottleneck Models with Semantic Locality for Better Interpretability

TL;DR

SL-CBM enhances concept bottleneck models by enforcing semantic locality, producing spatially coherent explanations that improve interpretability, debugging, and intervention without sacrificing classification accuracy.

Contribution

Introduces SL-CBM, a novel extension that enforces locality faithfulness in concept bottleneck models using spatially coherent saliency maps and attention mechanisms.

Findings

Significantly improves locality faithfulness and explanation quality.

Maintains competitive classification accuracy.

Enhances model interpretability and debugging capabilities.

Abstract

Explainable AI (XAI) is crucial for building transparent and trustworthy machine learning systems, especially in high-stakes domains. Concept Bottleneck Models (CBMs) have emerged as a promising ante-hoc approach that provides interpretable, concept-level explanations by explicitly modeling human-understandable concepts. However, existing CBMs often suffer from poor locality faithfulness, failing to spatially align concepts with meaningful image regions, which limits their interpretability and reliability. In this work, we propose SL-CBM (CBM with Semantic Locality), a novel extension that enforces locality faithfulness by generating spatially coherent saliency maps at both concept and class levels. SL-CBM integrates a 1x1 convolutional layer with a cross-attention mechanism to enhance alignment between concepts, image regions, and final predictions. Unlike prior methods, SL-CBM produces faithful saliency maps inherently tied to the model's internal reasoning, facilitating more effective debugging and intervention. Extensive experiments on image datasets demonstrate that SL-CBM substantially improves locality faithfulness, explanation quality, and intervention efficacy while maintaining competitive classification accuracy. Our ablation studies highlight the importance of contrastive and entropy-based regularization for balancing accuracy, sparsity, and faithfulness. Overall, SL-CBM bridges the gap between concept-based reasoning and spatial explainability, setting a new standard for interpretable and trustworthy concept-based models.