mlsanityData to 7 Oct 2026

Logic-Based Explainability: Past, Present & Future

arXiv 2406.11873 ↗First posted 4 Jun 2024cs.AIcited by 2

Not on the map. Why?

Abstract (arXiv)

In recent years, the impact of machine learning (ML) and artificial intelligence (AI) in society has been absolutely remarkable. This impact is expected to continue in the foreseeable future. However,the adoption of AI/ML is also a cause of grave concern. The operation of the most advances AI/ML models is often beyond the grasp of human decision makers. As a result, decisions that impact humans may not be understood and may lack rigorous validation. Explainable AI (XAI) is concerned with providing human decision-makers with understandable explanations for the predictions made by ML models. As a result, XAI is a cornerstone of trustworthy AI. Despite its strategic importance, most work on XAI lacks rigor, and so its use in high-risk or safety-critical domains serves to foster distrust instead of contributing to build much-needed trust. Logic-based XAI has recently emerged as a rigorous alternative to those other non-rigorous methods of XAI. This paper provides a technical survey of logic-based XAI, its origins, the current topics of research, and emerging future topics of research. The paper also highlights the many myths that pervade non-rigorous approaches for XAI.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 52 of its 115 references that are in the map. First posted on arXiv 4 Jun 2024.

Builds on

52 of 115 references.

References · 52

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  5. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
  6. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
  7. 2016The Mythos of Model Interpretabilitycited by 716
  8. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 364
  9. 2017Methods for Interpreting and Understanding Deep Neural Networkscited by 342
  10. 2019The many Shapley values for model explanationcited by 341
  11. 2018Actionable Recourse in Linear Classificationcited by 327
  12. 2020Problems with Shapley-value-based explanations as feature importance measurescited by 198
38 more
  1. 2018Abduction-Based Explanations for Machine Learning Modelscited by 159
  2. 2018A Symbolic Approach to Explaining Bayesian Network Classifierscited by 130
  3. 2020On The Reasons Behind Decisionscited by 99
  4. 2023First Three Years of the International Verification of Neural Networks Competition (VNN-COMP)cited by 58
  5. 2021On Explaining Random Forests with SATcited by 57
  6. 2020Explaining Naive Bayes and Other Linear Classifiers with Polynomial Time and Delaycited by 56
  7. 2021On Guaranteed Optimal Robust Explanations for NLP Modelscited by 54
  8. 2020On Explaining Decision Treescited by 49
  9. 2022Logic-Based Explainability in Machine Learningcited by 47
  10. 2022On Tackling Explanation Redundancy in Decision Treescited by 44
  11. 2021On the Computational Intelligibility of Boolean Classifierscited by 40
  12. 2021SAT-Based Rigorous Explanations for Decision Listscited by 40
  13. 2022On Computing Probabilistic Explanations for Decision Treescited by 35
  14. 2019On Validating, Repairing and Refining Heuristic ML Explanationscited by 32
  15. 2021On the Complexity of SHAP-Score-Based Explanations: Tractability via Knowledge Compilation and Non-Approximability Resultscited by 32
  16. 2021Trading Complexity for Sparsity in Random Forest Explanationscited by 32
  17. 2023The Inadequacy of Shapley Values for Explainabilitycited by 30
  18. 2022ASTERYX : A model-Agnostic SaT-basEd appRoach for sYmbolic and score-based eXplanationscited by 26
  19. 2022Eliminating The Impossible, Whatever Remains Must Be Truecited by 23
  20. 2022Computing Abductive Explanations for Boosted Treescited by 23
  21. 2023Explainability is NOT a Gamecited by 23
  22. 2022Feature Necessity & Relevancy in ML Classifier Explanationscited by 22
  23. 2024Distance-Restricted Explanations: Theoretical Underpinnings & Efficient Implementationcited by 20
  24. 2022On Computing Probabilistic Abductive Explanationscited by 18
  25. 2020Three Modern Roles for Logic in AIcited by 15
  26. 2023From Robustness to Explainability and Back Againcited by 14
  27. 2021Efficient Explanations With Relevant Setscited by 12
  28. 2023Disproving XAI Myths with Formal Methods -- Initial Resultscited by 12
  29. 2021Towards Rigorous Interpretations: a Formalisation of Feature Attributioncited by 11
  30. 2023On Formal Feature Attribution and Its Approximationcited by 11
  31. 2023Axiomatic Aggregations of Abductive Explanationscited by 10
  32. 2023Anytime Approximate Formal Feature Attributioncited by 9
  33. 2022Provably Precise, Succinct and Efficient Explanations for Decision Treescited by 8
  34. 2023A New Class of Explanations for Classifiers with Non-Binary Featurescited by 8
  35. 2024From SHAP Scores to Feature Importance Scorescited by 8
  36. 2023Locally-Minimal Probabilistic Explanationscited by 6
  37. 2022On Computing Relevant Features for Explaining NBCscited by 5
  38. 2023A Refutation of Shapley Values for Explainabilitycited by 4

50 most cited of 52 All 52 (JSON)

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025On the Complexity of Global Necessary Reasons to Explain Classificationcited by 3
  2. 2025Interpretable DNFscited by 0