mlsanityData to 7 Oct 2026

Label-Free Concept Bottleneck Models

arXiv 2304.06129 ↗First posted 12 Apr 2023cs.LG cs.CVcited by 282

Not on the map. Why?

Abstract (arXiv)

Concept bottleneck models (CBM) are a popular way of creating more interpretable neural networks by having hidden layer neurons correspond to human-understandable concepts. However, existing CBMs and their variants have two crucial limitations: first, they need to collect labeled data for each of the predefined concepts, which is time consuming and labor intensive; second, the accuracy of a CBM is often significantly lower than that of a standard neural network, especially on more complex datasets. This poor performance creates a barrier for adopting CBMs in practical real world applications. Motivated by these challenges, we propose Label-free CBM which is a novel framework to transform any neural network into an interpretable CBM without labeled concept data, while retaining a high accuracy. Our Label-free CBM has many advantages, it is: scalable - we present the first CBM scaled to ImageNet, efficient - creating a CBM takes only a few hours even for very large datasets, and automated - training it for a new dataset requires minimal human effort. Our code is available at https://github.com/Trustworthy-ML-Lab/Label-free-CBM. Finally, in Appendix B we conduct a large scale user evaluation of the interpretability of our method.

Key facts. Cited by 282 papers in the map (data through 7 Oct 2026). Builds on 16 of its 27 references that are in the map. First posted on arXiv 12 Apr 2023.

Builds on

16 of 27 references.

References · 16

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  5. 2022Locating and Editing Factual Associations in GPTcited by 2,609
  6. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
  7. 2020Concept Bottleneck Modelscited by 1,022
  8. 2022Post-hoc Concept Bottleneck Modelscited by 289
  9. 2020Concept Whitening for Interpretable Image Recognitioncited by 225
  10. 2022CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networkscited by 144
  11. 2020Rewriting a Deep Generative Modelcited by 105
  12. 2021Leveraging Sparse Linear Layers for Debuggable Deep Networkscited by 82
4 more
  1. 2022Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Offcited by 61
  2. 2019Interpretability Beyond Classification Output: Semantic Bottleneck Networkscited by 49
  3. 2020NBDT: Neural-Backed Decision Treescited by 46
  4. 2022Rewriting Geometric Rules of a GANcited by 25

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 23; 2024: 79; 2025: 93; 2026: 87.

282 papers.

Sort:

By area:

  1. 2024Sparse Feature Circuits: Discovering and Editing Interpretable Causal Graphs in Language Modelscited by 412
  2. 2024Interpreting CLIP with Sparse Linear Concept Embeddings (SpLiCE)cited by 116
  3. 2023Concept-based Explainable Artificial Intelligence: A Surveycited by 97
  4. 2024Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discoverycited by 91
  5. 2024VLG-CBM: Training Concept Bottleneck Models with Vision-Language Guidancecited by 65
  6. 2025Interpreting CLIP with Hierarchical Sparse Autoencoderscited by 54
  7. 2024Stochastic Concept Bottleneck Modelscited by 49
  8. 2024Incremental Residual Concept Bottleneck Modelscited by 43
  9. 2023Learning to Receive Help: Intervention-Aware Concept Embedding Modelscited by 41
  10. 2024Concept Bottleneck Large Language Modelscited by 41
  11. 2023Robust and Interpretable Medical Image Classifiers via Concept Bottleneck Modelscited by 40
  12. 2023Auxiliary Losses for Learning Generalizable Concept-based Modelscited by 35
38 more
  1. 2024Mammo-CLIP: A Vision Language Foundation Model to Enhance Data Efficiency and Robustness in Mammographycited by 35
  2. 2024Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic Interpretationscited by 33
  3. 2025Steering CLIP's vision transformer with sparse autoencoderscited by 33
  4. 2023Coarse-to-Fine Concept Bottleneck Modelscited by 31
  5. 2023Learning to Intervene on Concept Bottleneckscited by 29
  6. 2024Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?cited by 28
  7. 2024Causal Concept Graph Models: Beyond Causal Opacity in Deep Learningcited by 28
  8. 2025Derm1M: A Million-scale Vision-Language Dataset Aligned with Clinical Ontology Knowledge for Dermatologycited by 28
  9. 2025Language Guided Concept Bottleneck Models for Interpretable Continual Learningcited by 28
  10. 2024Decomposing Disease Descriptions for Enhanced Pathology Detection: A Multi-Aspect Vision-Language Pre-training Frameworkcited by 27
  11. 2023SI-MIL: Taming Deep MIL for Self-Interpretability in Gigapixel Histopathologycited by 25
  12. 2023Sparse Linear Concept Discovery Modelscited by 22
  13. 2023Interpretability is in the Mind of the Beholder: A Causal Framework for Human-interpretable Representation Learningcited by 22
  14. 2024Editable Concept Bottleneck Modelscited by 22
  15. 2023Concept Bottleneck with Visual Concept Filtering for Explainable Medical Image Classificationcited by 21
  16. 2024Semi-supervised Concept Bottleneck Modelscited by 21
  17. 2024Explain via Any Concept: Concept Bottleneck Model with Open Vocabulary Conceptscited by 20
  18. 2024A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcutscited by 19
  19. 2024Self-eXplainable AI for Medical Image Analysis: A Survey and New Outlookscited by 18
  20. 2025A Comprehensive Survey on Self-Interpretable Neural Networkscited by 18
  21. 2024Eliminating Information Leakage in Hard Concept Bottleneck Models with Supervised, Hierarchical Concept Learningcited by 17
  22. 2024Concept Bottleneck Models Without Predefined Conceptscited by 17
  23. 2024Integrating Clinical Knowledge into Concept Bottleneck Modelscited by 17
  24. 2024Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?cited by 17
  25. 2025Causally Reliable Concept Bottleneck Modelscited by 17
  26. 2024Bayesian Concept Bottleneck Models with LLM Priorscited by 16
  27. 2024DCBM: Data-Efficient Visual Concept Bottleneck Modelscited by 16
  28. 2024Concept Bottleneck Language Models For protein designcited by 15
  29. 2025If Concept Bottlenecks are the Question, are Foundation Models the Answer?cited by 15
  30. 2024A Textbook Remedy for Domain Shifts: Knowledge Priors for Medical Image Analysiscited by 14
  31. 2023From Neural Activations to Concepts: A Survey on Explaining Concepts in Neural Networkscited by 13
  32. 2023CLIP-QDA: An Explainable Concept Bottleneck Modelcited by 13
  33. 2024Understanding Inter-Concept Relationships in Concept-Based Modelscited by 13
  34. 2025Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lenscited by 13
  35. 2025Leakage and Interpretability in Concept-Based Modelscited by 13
  36. 2024AdaCBM: An Adaptive Concept Bottleneck Model for Explainable and Accurate Diagnosiscited by 12
  37. 2024Interpreting and Analysing CLIP's Zero-Shot Image Classification via Mutual Knowledgecited by 12
  38. 2024B-cosification: Transforming Deep Neural Networks to be Inherently Interpretablecited by 12

50 most cited of 282 All 282 (JSON)