{"type":"ScholarlyArticle","title":"Concept Bottleneck Models for Explainable Decision Making: A Survey of Progress, Taxonomy, and Future Directions","authors":[{"name":"Chunjiang Wang","slug":"chunjiang-wang","given":"Chunjiang","family":"Wang","affiliation":""},{"name":"Fan Li","slug":"fan-li","given":"Fan","family":"Li","affiliation":""},{"name":"Wenbo Hu","slug":"wenbo-hu","given":"Wenbo","family":"Hu","affiliation":""},{"name":"Rui Yan","slug":"rui-yan","given":"Rui","family":"Yan","affiliation":""},{"name":"Kun Zhang","slug":"kun-zhang","given":"Kun","family":"Zhang","affiliation":""},{"name":"Shaohua Kevin Zhou","slug":"shaohua-kevin-zhou","given":"Shaohua Kevin","family":"Zhou","affiliation":""}],"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.","doi":"10.24963/ijcai.2026/892","url":"https://ijcai.org/proceedings/2026/892","pdf":"https://ijcai.org/proceedings/2026/0892.pdf","markdown":"https://ijcai.org/proceedings/2026/892.md","bibtex":"https://ijcai.org/proceedings/2026/bibtex/892","volume":{"slug":"2026","title":"Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2026","url":"https://ijcai.org/proceedings/2026/","year":2026,"location":"Bremen, Germany","dates":"15-21 August 2026","editors":"Diego Calvanese","isbn":"978-1-956792-09-6","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2026"},"section":"Survey Track","track":"Survey Track","number":892,"pages":{"first":8041,"last":8049},"keywords":["AI Ethics, Trust, Fairnes: Explainability and interpretability"],"videos":[],"references":[],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}