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

2026-01-19

AI Summary

This work addresses the limited spatial locality in existing Concept Bottleneck Models (CBMs), which hinders precise alignment between concepts and semantically meaningful image regions, thereby undermining interpretability credibility. To overcome this limitation, the authors introduce, for the first time in CBMs, a combination of 1×1 convolutions and cross-attention mechanisms to generate faithful saliency maps tightly coupled with the model’s reasoning process. They further employ contrastive and entropy regularization to jointly optimize prediction accuracy, map sparsity, and explanation fidelity. Extensive experiments demonstrate that the proposed approach significantly improves local concept-region alignment, enhances explanation clarity, and boosts intervention effectiveness across multiple image datasets, all while maintaining competitive classification performance.

Technology Category

• Computer Vision: Interpretability, Explainability, and Transparency
• Machine Learning: Calibration & Uncertainty Quantification
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization

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.

Problem

• Concept Bottleneck Models
• locality faithfulness
• spatial alignment
• interpretable AI
• saliency maps

Innovation

• Concept Bottleneck Models
• Semantic Locality
• Local Faithfulness
• Saliency Maps
• Explainable AI