mlsanityData to 14 Oct 2026

Probabilistic Concept Bottleneck Models

arXiv 2306.01574 ↗First posted 2 Jun 2023cs.LG cs.AI cs.CVcited by 101

Not on the map. Why?

Abstract (arXiv)

Interpretable models are designed to make decisions in a human-interpretable manner. Representatively, Concept Bottleneck Models (CBM) follow a two-step process of concept prediction and class prediction based on the predicted concepts. CBM provides explanations with high-level concepts derived from concept predictions; thus, reliable concept predictions are important for trustworthiness. In this study, we address the ambiguity issue that can harm reliability. While the existence of a concept can often be ambiguous in the data, CBM predicts concepts deterministically without considering this ambiguity. To provide a reliable interpretation against this ambiguity, we propose Probabilistic Concept Bottleneck Models (ProbCBM). By leveraging probabilistic concept embeddings, ProbCBM models uncertainty in concept prediction and provides explanations based on the concept and its corresponding uncertainty. This uncertainty enhances the reliability of the explanations. Furthermore, as class uncertainty is derived from concept uncertainty in ProbCBM, we can explain class uncertainty by means of concept uncertainty. Code is publicly available at https://github.com/ejkim47/prob-cbm.

Key facts. Cited by 101 papers in the map (data through 14 Oct 2026). Builds on 29 of its 44 references that are in the map. First posted on arXiv 2 Jun 2023.

Builds on

29 of 44 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,498
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  4. 2016SGDR: Stochastic Gradient Descent with Warm Restartscited by 5,045
  5. 2015Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learningcited by 4,448
  6. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,371
  7. 2017What Uncertainties Do We Need in Bayesian Deep Learning for Computer Vision?cited by 2,352
  8. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,628
  9. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,319
  10. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,206
  11. 2020Concept Bottleneck Modelscited by 1,032
  12. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 737
17 more
  1. 2017Zero-Shot Learning -- A Comprehensive Evaluation of the Good, the Bad and the Uglycited by 538
  2. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  3. 2019Counterfactual Visual Explanationscited by 313
  4. 2022Post-hoc Concept Bottleneck Modelscited by 293
  5. 2020Concept Whitening for Interpretable Image Recognitioncited by 225
  6. 2019Probabilistic Face Embeddingscited by 173
  7. 2021Probabilistic Embeddings for Cross-Modal Retrievalcited by 151
  8. 2021Promises and Pitfalls of Black-Box Concept Learning Modelscited by 131
  9. 2022Interactive Concept Bottleneck Modelscited by 79
  10. 2022GlanceNets: Interpretabile, Leak-proof Concept-based Modelscited by 73
  11. 2018NSML: Meet the MLaaS platform with a real-world case studycited by 70
  12. 2023A Closer Look at the Intervention Procedure of Concept Bottleneck Modelscited by 64
  13. 2022Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Offcited by 61
  14. 2021Convolutional Dynamic Alignment Networks for Interpretable Classificationscited by 54
  15. 2021Meaningfully Debugging Model Mistakes using Conceptual Counterfactual Explanationscited by 53
  16. 2021A Framework for Learning Ante-hoc Explainable Models via Conceptscited by 45
  17. 2020iCaps: An Interpretable Classifier via Disentangled Capsule Networkscited by 7

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 9; 2024: 34; 2025: 32; 2026: 26.

101 papers.

Sort:

By area:

  1. 2023Concept-based Explainable Artificial Intelligence: A Surveycited by 98
  2. 2024Discover-then-Name: Task-Agnostic Concept Bottlenecks via Automated Concept Discoverycited by 91
  3. 2024Stochastic Concept Bottleneck Modelscited by 51
  4. 2023Learning to Receive Help: Intervention-Aware Concept Embedding Modelscited by 41
  5. 2024BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcutscited by 37
  6. 2023Auxiliary Losses for Learning Generalizable Concept-based Modelscited by 35
  7. 2024Energy-Based Concept Bottleneck Models: Unifying Prediction, Concept Intervention, and Probabilistic Interpretationscited by 33
  8. 2023Coarse-to-Fine Concept Bottleneck Modelscited by 31
  9. 2023Learning to Intervene on Concept Bottleneckscited by 29
  10. 2024Causal Concept Graph Models: Beyond Causal Opacity in Deep Learningcited by 29
  11. 2024Beyond Concept Bottleneck Models: How to Make Black Boxes Intervenable?cited by 28
  12. 2024Editable Concept Bottleneck Modelscited by 23
38 more
  1. 2024Semi-supervised Concept Bottleneck Modelscited by 21
  2. 2024A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcutscited by 19
  3. 2025A Comprehensive Survey on Self-Interpretable Neural Networkscited by 18
  4. 2024Learning Discrete Concepts in Latent Hierarchical Modelscited by 17
  5. 2024Interpretable Concept-Based Memory Reasoningcited by 17
  6. 2024Bayesian Concept Bottleneck Models with LLM Priorscited by 17
  7. 2025Causally Reliable Concept Bottleneck Modelscited by 17
  8. 2023Relational Concept Bottleneck Modelscited by 15
  9. 2025If Concept Bottlenecks are the Question, are Foundation Models the Answer?cited by 15
  10. 2024Neural Concept Bindercited by 14
  11. 2024Understanding Inter-Concept Relationships in Concept-Based Modelscited by 13
  12. 2025Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lenscited by 13
  13. 2025Leakage and Interpretability in Concept-Based Modelscited by 13
  14. 2025Explain Yourself, Briefly! Self-Explaining Neural Networks with Concise Sufficient Reasonscited by 12
  15. 2024Concept-Attention Whitening for Interpretable Skin Lesion Diagnosiscited by 11
  16. 2024Do Concept Bottleneck Models Respect Localities?cited by 10
  17. 2024Pretrained Visual Uncertaintiescited by 10
  18. 2025Avoiding Leakage Poisoning: Concept Interventions Under Distribution Shiftscited by 9
  19. 2025Graph Concept Bottleneck Modelscited by 9
  20. 2024Tree-Based Leakage Inspection and Control in Concept Bottleneck Modelscited by 8
  21. 2024Counterfactual Concept Bottleneck Modelscited by 7
  22. 2024Evidential Concept Embedding Models: Towards Reliable Concept Explanations for Skin Disease Diagnosiscited by 7
  23. 2025Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimizationcited by 7
  24. 2024Improving Intervention Efficacy via Concept Realignment in Concept Bottleneck Modelscited by 6
  25. 2024EQ-CBM: A Probabilistic Concept Bottleneck with Energy-based Models and Quantized Vectorscited by 6
  26. 2024Towards Multi-dimensional Explanation Alignment for Medical Classificationcited by 6
  27. 2025Neural Probabilistic Circuits: Enabling Compositional and Interpretable Predictions through Logical Reasoningcited by 6
  28. 2023Transparent Anomaly Detection via Concept-based Explanationscited by 5
  29. 2023Benchmarking and Enhancing Disentanglement in Concept-Residual Modelscited by 5
  30. 2025LogicCBMs: Logic-Enhanced Concept-Based Learningcited by 5
  31. 2024Improving deep learning with prior knowledge and cognitive models: A survey on enhancing explainability, adversarial robustness and zero-shot learningcited by 4
  32. 2024Improving Concept Alignment in Vision-Language Concept Bottleneck Modelscited by 4
  33. 2025A Comprehensive Survey on the Risks and Limitations of Concept-based Modelscited by 4
  34. 2025MVP-CBM:Multi-layer Visual Preference-enhanced Concept Bottleneck Model for Explainable Medical Image Classificationcited by 4
  35. 2025Locality-aware Concept Bottleneck Modelcited by 4
  36. 2024Incorporating Expert Rules into Neural Networks in the Framework of Concept-Based Learningcited by 3
  37. 2024Linearly-Interpretable Concept Embedding Models for Text Analysiscited by 3
  38. 2025V-CEM: Bridging Performance and Intervenability in Concept-based Modelscited by 3

50 most cited of 101 All 101 (JSON)