mlsanityData to 7 Oct 2026

Interactive Concept Bottleneck Models

arXiv 2212.07430 ↗First posted 14 Dec 2022cs.LG cs.AIcited by 79

Not on the map. Why?

Abstract (arXiv)

Concept bottleneck models (CBMs) are interpretable neural networks that first predict labels for human-interpretable concepts relevant to the prediction task, and then predict the final label based on the concept label predictions. We extend CBMs to interactive prediction settings where the model can query a human collaborator for the label to some concepts. We develop an interaction policy that, at prediction time, chooses which concepts to request a label for so as to maximally improve the final prediction. We demonstrate that a simple policy combining concept prediction uncertainty and influence of the concept on the final prediction achieves strong performance and outperforms static approaches as well as active feature acquisition methods proposed in the literature. We show that the interactive CBM can achieve accuracy gains of 5-10% with only 5 interactions over competitive baselines on the Caltech-UCSD Birds, CheXpert and OAI datasets.

Key facts. Cited by 79 papers in the map (data through 7 Oct 2026). Builds on 7 of its 15 references that are in the map. First posted on arXiv 14 Dec 2022.

Builds on

7 of 15 references.

References · 7

  1. 2019CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparisoncited by 1,410
  2. 2020Concept Bottleneck Modelscited by 1,022
  3. 2020Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performancecited by 396
  4. 2018EDDI: Efficient Dynamic Discovery of High-Value Information with Partial VAEcited by 85
  5. 2020Active Feature Acquisition with Generative Surrogate Modelscited by 53
  6. 2020Debiasing Concept-based Explanations with Causal Analysiscited by 32
  7. 2021Rationalization through Conceptscited by 19

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 13; 2024: 27; 2025: 21; 2026: 18.

79 papers.

Sort:

By area:

  1. 2023Probabilistic Concept Bottleneck Modelscited by 101
  2. 2024Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discoverycited by 91
  3. 2023A Closer Look at the Intervention Procedure of Concept Bottleneck Modelscited by 63
  4. 2024Stochastic Concept Bottleneck Modelscited by 49
  5. 2023Learning to Receive Help: Intervention-Aware Concept Embedding Modelscited by 41
  6. 2023Robust and Interpretable Medical Image Classifiers via Concept Bottleneck Modelscited by 40
  7. 2023Human Uncertainty in Concept-Based AI Systemscited by 39
  8. 2023Auxiliary Losses for Learning Generalizable Concept-based Modelscited by 35
  9. 2023Learning to Intervene on Concept Bottleneckscited by 29
  10. 2024Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?cited by 28
  11. 2024Interpretable Concept Bottlenecks to Align Reinforcement Learning Agentscited by 23
  12. 2023Interpretability is in the Mind of the Beholder: A Causal Framework for Human-interpretable Representation Learningcited by 22
38 more
  1. 2024Editable Concept Bottleneck Modelscited by 22
  2. 2024Semi-supervised Concept Bottleneck Modelscited by 21
  3. 2024Self-eXplainable AI for Medical Image Analysis: A Survey and New Outlookscited by 18
  4. 2025A Comprehensive Survey on Self-Interpretable Neural Networkscited by 18
  5. 2024Learning Discrete Concepts in Latent Hierarchical Modelscited by 17
  6. 2024Pre-trained Vision-Language Models Learn Discoverable Visual Conceptscited by 16
  7. 2025If Concept Bottlenecks are the Question, are Foundation Models the Answer?cited by 15
  8. 2024Understanding Inter-Concept Relationships in Concept-Based Modelscited by 13
  9. 2025Leakage and Interpretability in Concept-Based Modelscited by 13
  10. 2025Discovering Fine-Grained Visual-Concept Relations by Disentangled Optimal Transport Concept Bottleneck Modelscited by 12
  11. 2024Do Concept Bottleneck Models Respect Localities?cited by 10
  12. 2023A Framework for Interpretability in Machine Learning for Medical Imagingcited by 9
  13. 2024Towards Interpretable Radiology Report Generation via Concept Bottlenecks using a Multi-Agentic RAGcited by 9
  14. 2025Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shiftscited by 9
  15. 2026Human-AI Co-design for Clinical Prediction Modelscited by 9
  16. 2025Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimizationcited by 7
  17. 2023Selective Concept Models: Permitting Stakeholder Customisation at Test-Timecited by 6
  18. 2024Improving Intervention Efficacy via Concept Realignment in Concept Bottleneck Modelscited by 6
  19. 2024EQ-CBM: A Probabilistic Concept Bottleneck with Energy-based Models and Quantized Vectorscited by 6
  20. 2024Towards Multi-dimensional Explanation Alignment for Medical Classificationcited by 6
  21. 2023Transparent Anomaly Detection via Concept-based Explanationscited by 5
  22. 2023Benchmarking and Enhancing Disentanglement in Concept-Residual Modelscited by 5
  23. 2025LogicCBMs: Logic-Enhanced Concept-Based Learningcited by 5
  24. 2023A Survey of Explainable AI in Deep Visual Modeling: Methods and Metricscited by 4
  25. 2024Can we Constrain Concept Bottleneck Models to Learn Semantically Meaningful Input Features?cited by 4
  26. 2024Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learningcited by 4
  27. 2024LICORICE: Label-Efficient Concept-Based Interpretable Reinforcement Learningcited by 4
  28. 2024Learning New Concepts, Remembering the Old: Continual Learning for Multimodal Concept Bottleneck Modelscited by 4
  29. 2025CBVLM: Training-free Explainable Concept-based Large Vision Language Models for Medical Image Classificationcited by 4
  30. 2025A Comprehensive Survey on the Risks and Limitations of Concept-based Modelscited by 4
  31. 2026Actionable Interpretability Must Be Defined in Terms of Symmetriescited by 4
  32. 2024Incorporating Expert Rules into Neural Networks in the Framework of Concept-Based Learningcited by 3
  33. 2024Concept Complement Bottleneck Model for Interpretable Medical Image Diagnosiscited by 3
  34. 2024Guarding the Gate: ConceptGuard Battles Concept-Level Backdoors in Concept Bottleneck Modelscited by 3
  35. 2025Stable Vision Concept Transformers for Medical Diagnosiscited by 3
  36. 2025Interpretable Reward Modeling with Active Concept Bottleneckscited by 3
  37. 2025A Geometric Unification of Concept Learning with Concept Conescited by 3
  38. 2024MINT: A wrapper to make multi-modal and multi-image AI models interactivecited by 2

50 most cited of 79 All 79 (JSON)