mlsanityData to 7 Oct 2026

Concept-based Explainable Artificial Intelligence: A Survey

arXiv 2312.12936 ↗First posted 20 Dec 2023cs.AI cs.HCcited by 97

Not on the map. Why?

Abstract (arXiv)

The field of explainable artificial intelligence emerged in response to the growing need for more transparent and reliable models. However, using raw features to provide explanations has been disputed in several works lately, advocating for more user-understandable explanations. To address this issue, a wide range of papers proposing Concept-based eXplainable Artificial Intelligence (C-XAI) methods have arisen in recent years. Nevertheless, a unified categorization and precise field definition are still missing. This paper fills the gap by offering a thorough review of C-XAI approaches. We define and identify different concepts and explanation types. We provide a taxonomy identifying nine categories and propose guidelines for selecting a suitable category based on the development context. Additionally, we report common evaluation strategies including metrics, human evaluations and dataset employed, aiming to assist the development of future methods. We believe this survey will serve researchers, practitioners, and domain experts in comprehending and advancing this innovative field.

Key facts. Cited by 97 papers in the map (data through 7 Oct 2026). Builds on 92 of its 153 references that are in the map. First posted on arXiv 20 Dec 2023.

Builds on

92 of 153 references.

References · 92

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Language Models are Few-Shot Learnerscited by 32,199
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  5. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  6. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  7. 2022BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generationcited by 4,310
  8. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  9. 2014Deep Learning Face Attributes in the Wildcited by 3,679
  10. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  11. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
  12. 2013Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Mapscited by 2,348
38 more
  1. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  2. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,543
  3. 2017Deformable Convolutional Networkscited by 1,481
  4. 2017Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)cited by 1,309
  5. 2018Sanity Checks for Saliency Mapscited by 1,149
  6. 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,065
  7. 2020Concept Bottleneck Modelscited by 1,022
  8. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
  9. 2018This Looks Like That: Deep Learning for Interpretable Image Recognitioncited by 731
  10. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 703
  11. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  12. 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 467
  13. 2017Interpretation of Neural Networks is Fragilecited by 443
  14. 2019Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methodscited by 440
  15. 2016European Union regulations on algorithmic decision-making and a "right to explanation"cited by 343
  16. 2017The (Un)reliability of saliency methodscited by 331
  17. 2020Neural Additive Models: Interpretable Machine Learning with Neural Netscited by 318
  18. 2022Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classificationcited by 310
  19. 2019A Short Note on the Kinetics-700 Human Action Datasetcited by 308
  20. 2022Post-hoc Concept Bottleneck Modelscited by 289
  21. 2023Label-Free Concept Bottleneck Modelscited by 282
  22. 2018Manipulating and Measuring Model Interpretabilitycited by 256
  23. 2018Learning Not to Learn: Training Deep Neural Networks with Biased Datacited by 255
  24. 2020Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Surveycited by 252
  25. 2019On Completeness-aware Concept-Based Explanations in Deep Neural Networkscited by 239
  26. 2017Deep Learning for Case-Based Reasoning through Prototypes: A Neural Network that Explains Its Predictionscited by 234
  27. 2020Concept Whitening for Interpretable Image Recognitioncited by 225
  28. 2014Object Detectors Emerge in Deep Scene CNNscited by 178
  29. 2022CRAFT: Concept Recursive Activation FacTorization for Explainabilitycited by 177
  30. 2020Compositional Explanations of Neuronscited by 172
  31. 2018Local Rule-Based Explanations of Black Box Decision Systemscited by 165
  32. 2017Interpretable Convolutional Neural Networkscited by 161
  33. 2022CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networkscited by 144
  34. 2022From Attribution Maps to Human-Understandable Explanations through Concept Relevance Propagationcited by 141
  35. 2021Benchmarking and Survey of Explanation Methods for Black Box Modelscited by 136
  36. 2019Explaining Classifiers with Causal Concept Effect (CaCE)cited by 135
  37. 2018Net2Vec: Quantifying and Explaining how Concepts are Encoded by Filters in Deep Neural Networkscited by 128
  38. 2021Promises and Pitfalls of Black-Box Concept Learning Modelscited by 128

50 most cited of 92 All 92 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 21; 2025: 41; 2026: 35.

97 papers.

Sort:

By area:

  1. 2024BEARS Make Neuro-Symbolic Models Aware of their Reasoning Shortcutscited by 36
  2. 2024A Neuro-Symbolic Benchmark Suite for Concept Quality and Reasoning Shortcutscited by 19
  3. 2024Self-eXplainable AI for Medical Image Analysis: A Survey and New Outlookscited by 18
  4. 2024Interpretable Concept-Based Memory Reasoningcited by 17
  5. 2024Concept-Based Explanations in Computer Vision: Where Are We and Where Could We Go?cited by 17
  6. 2025Causally Reliable Concept Bottleneck Modelscited by 17
  7. 2024Unsupervised Concept Drift Detection from Deep Learning Representations in Real-timecited by 16
  8. 2025If Concept Bottlenecks are the Question, are Foundation Models the Answer?cited by 15
  9. 2025Shortcuts and Identifiability in Concept-based Models from a Neuro-Symbolic Lenscited by 13
  10. 2025VL-SAE: Interpreting and Enhancing Vision-Language Alignment with a Unified Concept Setcited by 12
  11. 2024Concept-Attention Whitening for Interpretable Skin Lesion Diagnosiscited by 11
  12. 2024Generating Counterfactual Trajectories with Latent Diffusion Models for Concept Discoverycited by 8
38 more
  1. 2025Addressing Concept Mislabeling in Concept Bottleneck Models Through Preference Optimizationcited by 7
  2. 2025Towards Achieving Concept Completeness for Textual Concept Bottleneck Modelscited by 6
  3. 2025Representational Similarity via Interpretable Visual Conceptscited by 5
  4. 2024Understanding Multimodal Deep Neural Networks: A Concept Selection Viewcited by 4
  5. 2024LICORICE: Label-Efficient Concept-Based Interpretable Reinforcement Learningcited by 4
  6. 2024Interpretability for Time Series Transformers using A Concept Bottleneck Frameworkcited by 4
  7. 2025An Explainable Biomedical Foundation Model via Large-Scale Concept-Enhanced Vision-Language Pre-trainingcited by 4
  8. 2025A Comprehensive Survey on the Risks and Limitations of Concept-based Modelscited by 4
  9. 2026Actionable Interpretability Must Be Defined in Terms of Symmetriescited by 4
  10. 2024Linearly-Interpretable Concept Embedding Models for Text Analysiscited by 3
  11. 2024This Probably Looks Exactly Like That: An Invertible Prototypical Networkcited by 3
  12. 2025V-CEM: Bridging Performance and Intervenability in Concept-based Modelscited by 3
  13. 2025C-SHAP for time series: An approach to high-level temporal explanationscited by 3
  14. 2025Interpretable Hierarchical Concept Reasoning through Attention-Guided Graph Learningcited by 3
  15. 2025Unveiling Decision-Making in LLMs for Text Classification : Extraction of influential and interpretable concepts with Sparse Autoencoderscited by 3
  16. 2025On The Variability of Concept Activation Vectorscited by 3
  17. 2025Nonparametric Identification of Latent Conceptscited by 3
  18. 2025Quantifying the Accuracy-Interpretability Trade-Off in Concept-Based Sidechannel Modelscited by 3
  19. 2025A Geometric Unification of Concept Learning with Concept Conescited by 3
  20. 2026Cross-Lingual LLM-Judge Transfer via Evaluation Decompositioncited by 3
  21. 2024Knowledge graphs for empirical concept retrievalcited by 2
  22. 2024Quanda: An Interpretability Toolkit for Training Data Attribution Evaluation and Beyondcited by 2
  23. 2025Multi-Domain Explainability of Preferencescited by 2
  24. 2025Towards Reasonable Concept Bottleneck Modelscited by 2
  25. 2025Concept-based Adversarial Attack: a Probabilistic Perspectivecited by 2
  26. 2025A Survey on Interpretability in Visual Recognitioncited by 2
  27. 2025Debugging Concept Bottleneck Models through Removal and Retrainingcited by 2
  28. 2026Mixture of Concept Bottleneck Expertscited by 2
  29. 2026Rethinking Concept Bottleneck Models: From Pitfalls to Solutionscited by 2
  30. 2024When a Relation Tells More Than a Concept: Exploring and Evaluating Classifier Decisions with CoReXcited by 1
  31. 2024LatentExplainer: Explaining Latent Representations in Deep Generative Models with Multimodal Large Language Modelscited by 1
  32. 2024FI-CBL: A Probabilistic Method for Concept-Based Learning with Expert Rulescited by 1
  33. 2024Beyond Attribution: Unified Concept-Level Explanationscited by 1
  34. 2025Rule-Bottleneck Reinforcement Learning: Joint Explanation and Decision Optimization for Resource Allocation with Language Agentscited by 1
  35. 2025Logic Explanation of AI Classifiers by Categorical Explaining Functorscited by 1
  36. 2025On Background Bias of Post-Hoc Concept Embeddings in Computer Vision DNNscited by 1
  37. 2025CUBIC: Concept Embeddings for Unsupervised Bias Identification using VLMscited by 1
  38. 2025Enhancing the Comprehensibility of Text Explanations via Unsupervised Concept Discoverycited by 1

50 most cited of 97 All 97 (JSON)