Proceedings

Concept Bottleneck Models for Explainable Decision Making: A Survey of Progress, Taxonomy, and Future Directions

Chunjiang Wang, Fan Li, Wenbo Hu, Rui Yan, Kun Zhang, Shaohua Kevin Zhou

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. Survey Track. Pages 8041-8049.

https://doi.org/10.24963/ijcai.2026/892

Keywords

  • AI Ethics, Trust, Fairnes: Explainability and interpretability

Abstract

Deep neural networks deliver strong performance but remain opaque, limiting their use in high-stakes domains that require transparency and human oversight. Concept Bottleneck Models (CBMs) address this gap by introducing a human-interpretable concept layer that mediates inputs and decisions, enabling semantic explanations and test-time intervention. This survey provides a unified review of CBMs organized along four dimensions: concept acquisition, concept-based decision making, concept intervention, and concept evaluation. We summarize the evolution of concept construction from manual annotation to lexicon-based mining, LLM/VLM-guided generation, and visually grounded discovery via prototypes and diffusion models; review emerging CBM architectures beyond strict bottlenecks; and consolidate evaluation and intervention protocols emphasizing faithfulness, sparsity, and intervenability, with particular relevance to high-stakes domains such as healthcare. We synthesize fragmented literature and outline key challenges and future directions for concept-based interpretable decision making.

Chunjiang Wang, Fan Li, Wenbo Hu, Rui Yan, Kun Zhang, and Shaohua Kevin Zhou. 2026. Concept Bottleneck Models for Explainable Decision Making: A Survey of Progress, Taxonomy, and Future Directions. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 8041–8049. https://doi.org/10.24963/ijcai.2026/892
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards