mlsanityData to 7 Oct 2026

A Survey Of Methods For Explaining Black Box Models

arXiv 1802.01933 ↗First posted 6 Feb 2018cs.CY cs.AI cs.LGcited by 970

Not on the map. Why?

Abstract (arXiv)

In the last years many accurate decision support systems have been constructed as black boxes, that is as systems that hide their internal logic to the user. This lack of explanation constitutes both a practical and an ethical issue. The literature reports many approaches aimed at overcoming this crucial weakness sometimes at the cost of scarifying accuracy for interpretability. The applications in which black box decision systems can be used are various, and each approach is typically developed to provide a solution for a specific problem and, as a consequence, delineating explicitly or implicitly its own definition of interpretability and explanation. The aim of this paper is to provide a classification of the main problems addressed in the literature with respect to the notion of explanation and the type of black box system. Given a problem definition, a black box type, and a desired explanation this survey should help the researcher to find the proposals more useful for his own work. The proposed classification of approaches to open black box models should also be useful for putting the many research open questions in perspective.

Key facts. Cited by 970 papers in the map (data through 7 Oct 2026). First posted on arXiv 6 Feb 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2019: 1; 2020: 0; 2021: 192; 2022: 189; 2023: 186; 2024: 166; 2025: 140; 2026: 96.

970 papers.

Sort:

By area:

  1. 2023Large Language Modelscited by 774
  2. 2021Deep Neural Networks and Tabular Data: A Surveycited by 489
  3. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 299
  4. 2021Trustworthy AI: From Principles to Practicescited by 206
  5. 2021Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyondcited by 177
  6. 2023Should ChatGPT be Biased? Challenges and Risks of Bias in Large Language Modelscited by 144
  7. 2023Interactive and Explainable Region-guided Radiology Report Generationcited by 139
  8. 2021Benchmarking and Survey of Explanation Methods for Black Box Modelscited by 136
  9. 2021Teach Me to Explain: A Review of Datasets for Explainable Natural Language Processingcited by 126
  10. 2021Explainable AI (XAI): A Systematic Meta-Survey of Current Challenges and Future Opportunitiescited by 125
  11. 2022OpenXAI: Towards a Transparent Evaluation of Model Explanationscited by 125
  12. 2021Human-Centered Explainable AI (XAI): From Algorithms to User Experiencescited by 123
38 more
  1. 2023Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directionscited by 123
  2. 2021What Do We Want From Explainable Artificial Intelligence (XAI)? -- A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Researchcited by 119
  3. 2021CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networkscited by 118
  4. 2022XAI for Transformers: Better Explanations through Conservative Propagationcited by 100
  5. 2021A Clarification of the Nuances in the Fairness Metrics Landscapecited by 98
  6. 2023Concept-based Explainable Artificial Intelligence: A Surveycited by 97
  7. 2021Trustworthy AI: A Computational Perspectivecited by 93
  8. 2021A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Conceptscited by 90
  9. 2021CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithmscited by 85
  10. 2021A Survey on Bias in Visual Datasetscited by 84
  11. 2022Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanationscited by 84
  12. 2021Explainability of deep vision-based autonomous driving systems: Review and challengescited by 80
  13. 2021Explanations in Autonomous Driving: A Surveycited by 80
  14. 2022GlanceNets: Interpretabile, Leak-proof Concept-based Modelscited by 73
  15. 2023Understanding the Role of Human Intuition on Reliance in Human-AI Decision-Making with Explanationscited by 73
  16. 2021Argumentative XAI: A Surveycited by 66
  17. 2022Human-AI Collaboration via Conditional Delegation: A Case Study of Content Moderationcited by 66
  18. 2022"Help Me Help the AI": Understanding How Explainability Can Support Human-AI Interactioncited by 63
  19. 2021NICE: An Algorithm for Nearest Instance Counterfactual Explanationscited by 62
  20. 2022Interactive Model Cards: A Human-Centered Approach to Model Documentationcited by 61
  21. 2021Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applicationscited by 59
  22. 2021On Explaining Random Forests with SATcited by 57
  23. 2021Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactualscited by 55
  24. 2022CEBaB: Estimating the Causal Effects of Real-World Concepts on NLP Model Behaviorcited by 54
  25. 2023On Early Detection of Hallucinations in Factual Question Answeringcited by 54
  26. 2021Software for Dataset-wide XAI: From Local Explanations to Global Insights with Zennit, CoRelAy, and ViRelAycited by 53
  27. 2022Rethinking Explainability as a Dialogue: A Practitioner's Perspectivecited by 52
  28. 2022Leveraging Explanations in Interactive Machine Learning: An Overviewcited by 52
  29. 2021GLocalX -- From Local to Global Explanations of Black Box AI Modelscited by 48
  30. 2021The Who in XAI: How AI Background Shapes Perceptions of AI Explanationscited by 48
  31. 2022Designing for Responsible Trust in AI Systems: A Communication Perspectivecited by 48
  32. 2022Investigating Explainability of Generative AI for Code through Scenario-based Designcited by 47
  33. 2022Logic-Based Explainability in Machine Learningcited by 47
  34. 2023Adversarial attacks and defenses in explainable artificial intelligence: A surveycited by 47
  35. 2021A Review on Explainability in Multimodal Deep Neural Netscited by 46
  36. 2024Explainable Artificial Intelligence: A Survey of Needs, Techniques, Applications, and Future Directioncited by 46
  37. 2022On Tackling Explanation Redundancy in Decision Treescited by 44
  38. 2023Faithful Explanations of Black-box NLP Models Using LLM-generated Counterfactualscited by 44

50 most cited of 970 All 970 (JSON)