Concept Bottleneck Models

Also known as CBM

Overview

Concept Bottleneck Models predict through an intermediate set of meaningful attributes, such as visual features or clinical findings, so people can examine how those concepts contribute to an output. Approaches include supervised concept predictors with simple classifiers, vision-language models that propose concepts, and structured bottlenecks that model concept relations, hierarchies, or spatial locations. The methods are tested in settings such as fine-grained image classification, medical diagnosis, text and graph prediction, and multimodal tasks, with evaluation increasingly examining concept accuracy and interventions as well as task accuracy. A central tension is that incomplete or noisy concepts can hurt predictions, while information leakage can preserve accuracy but make explanations or user interventions unreliable.

Latest papers

CardsList

92 papers9 papers in the last four weeks, down 18% on the four weeks before. 0.1% of all new papers.

  1. CBX-Bench: A Human-Aligned MLLM Council for Benchmarking Concept Bottleneck Model Explanations

    Aug 15, 2026Yusuf Meric Karadag, Gulay Oklan, Seref Baris Cagliyan +2Explainability EvaluationConcept Bottleneck Models

  2. Less Annotation, More Interpretation: Prior-Guided Concept Bottleneck Models for Interpretable Cancer Imaging Diagnosis

    Aug 13, 2026Baoqiang Ma, Kenneth GilhuijsConcept Bottleneck ModelsMedical Image Classification

  3. Distilling CT Foundation Models into Editable Concept Bottlenecks for Lung Nodule Malignancy Prediction

    Aug 8, 2026Fakrul Islam Tushar, Stephen Adamo, Geoffrey D. RubinMedical Imaging Foundation ModelsConcept Bottleneck Models

  4. ReCBM: Uncertainty-Gated Relational Reasoning for Concept Bottleneck Models

    Aug 7, 2026An Sui, Yuzhu Li, Fuping Wu +1Concept Bottleneck Models

  5. Open-Linguistic Concept Unified Learning for Cross-Site Interpretable Dermatology Image Diagnosis

    Aug 4, 2026Chengyu Wu, Junpeng Tan, Wanxiang Luo +3Concept Bottleneck ModelsMedical Diagnosis

  6. Loss Invariance Determines What Concept Layers Encode: Volume Grounding in Echocardiography

    Jul 28, 2026Hyunkyung Han, Min Jung KimConcept Bottleneck ModelsLeft Ventricular Ejection Fraction Estimation

  7. Spatially Grounded Concept Bottleneck Models for Trustworthy Breast Ultrasound Diagnosis

    Jul 22, 2026Moshiur Rahman Tonmoy, Dunren Che, Haitham Y. Adarbah +1Concept Bottleneck ModelsMedical Image Classification

  8. Explainable Novel Category Discovery in Semantic Concept Space

    Jul 5, 2026Ifrat Ikhtear Uddin, Yang Zhou, Chaowei Zhang +1Concept Bottleneck ModelsConcept-Based Explanations

  9. Beyond Heatmaps: Unsupervised Concept-Graph Reasoning for Interpretable Visual Explanation

    Jul 1, 2026Md Mohasin Hossain, Anar Amirli, Robert Leist +2Concept Bottleneck ModelsConcept-Based Explanations

  10. Caption Bottleneck Models

    Jul 1, 2026Seref Baris Cagliyan, Umut Ozdemir, Merve Tapli +1Vision-Language ModelsConcept Bottleneck Models

  11. On the Faithfulness of Post-Hoc Concept Bottleneck Models

    Jun 29, 2026Laines Schmalwasser, Jan Blunk, Niklas Penzel +2Concept Bottleneck ModelsExplainability Evaluation

  12. TRACE: A Concept Bottleneck Model for Longitudinal 3D Glioblastoma Response Assessment

    Jun 29, 2026Alia Tarek, Hamsa Saberr, Hamza Elghonemy +6Concept Bottleneck Models3D Medical Imaging

  13. Bridging Vision and Language Concepts through Optimal Transport Semantic Flow

    Jun 25, 2026Chenyang Zhang, Anqi Dong, Guangming Zhu +4Concept Bottleneck ModelsVLM Interpretability

  14. Multimodal Concept Bottleneck Models

    Jun 18, 2026Tongqing Shi, Ge Yan, Tuomas Oikarinen +1Concept Bottleneck ModelsVLM Interpretability

  15. Concept Flow Models: Anchoring Concept-Based Reasoning with Hierarchical Bottlenecks

    Jun 17, 2026Ya Wang, Adrian PaschkeConcept Bottleneck Models

  16. Assessing Reliability of Symbol Detection in Concept Bottleneck Models

    Jun 15, 2026Javier Fumanal-Idocin, Javier Andreu-PerezConcept Bottleneck ModelsShortcut Learning

  17. 3D-CBM: A Framework for Concept-Based Interpretability in Generative 3D Modeling

    Jun 9, 2026Ahmad Al-KabbanyConcept Bottleneck ModelsInterpretable ML

  18. scCBGM: Interpretable Single-Cell Counterfactual Editing

    Jun 5, 2026Alma Andersson, Aya Abdelsalam Ismail, Edward De Brouwer +6Concept Bottleneck ModelsCausal Counterfactual Generation

  19. Measuring What Matters: Synthetic Benchmarks for Concept Bottleneck Models

    Jun 3, 2026Julian Skirzynski, Harry Cheon, Shreyas Kadekodi +2Concept Bottleneck ModelsBenchmark Design

  20. ConceptM3^3oE: Concept-Guided Multimodal Mixture of Experts for Interpretable Computational Pathology

    May 23, 2026Xuan Wang, Zhongling Xu, Gopi Kannedhara +13Computational PathologyConcept Bottleneck Models

  21. Hoeffding Concept Bottleneck Models with Applications to Overhead Images

    May 22, 2026Clément Bénard, Manon Arfib, Christophe Labreuche +1Concept Bottleneck ModelsExplainable Image Classification

  22. SynCB: A Synergy Concept-Based Model with Dynamic Routing Between Concepts and Complementary Neural Branches

    May 20, 2026Tores Julie, Sun Rémy, Sassatelli Lucile +3Concept Bottleneck Models

  23. Matryoshka Concept Bottleneck Models

    May 20, 2026Ziye Chen, Hongbin Lin, Jie Li +1Concept Bottleneck ModelsHuman-in-the-Loop AI

  24. CLIF: Concept-Level Influence Functions for Transparent Bottleneck Models

    May 19, 2026Yike Sun, Mingkun Xu, Mu You +5Concept Bottleneck ModelsInfluence Functions

  25. Concise and Logically Consistent Conformal Sets for Neuro-Symbolic Concept-Based Models

    May 18, 2026Samuele Bortolotti, Emanuele Marconato, Andrea Pugnana +2Concept Bottleneck ModelsConformal Prediction

  26. Towards Fine-Grained and Verifiable Concept Bottleneck Models

    May 14, 2026Yingying Fang, Haijie Xu, Shuang Wu +2Concept Bottleneck ModelsNeural Network Interpretability