mlsanityData to 7 Oct 2026

Disproving XAI Myths with Formal Methods -- Initial Results

arXiv 2306.01744 ↗First posted 13 May 2023cs.AI cs.LGcited by 12

Not on the map. Why?

Abstract (arXiv)

The advances in Machine Learning (ML) in recent years have been both impressive and far-reaching. However, the deployment of ML models is still impaired by a lack of trust in how the best-performing ML models make predictions. The issue of lack of trust is even more acute in the uses of ML models in high-risk or safety-critical domains. eXplainable artificial intelligence (XAI) is at the core of ongoing efforts for delivering trustworthy AI. Unfortunately, XAI is riddled with critical misconceptions, that foster distrust instead of building trust. This paper details some of the most visible misconceptions in XAI, and shows how formal methods have been used, both to disprove those misconceptions, but also to devise practically effective alternatives.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 42 of its 89 references that are in the map. First posted on arXiv 13 May 2023.

Builds on

42 of 89 references.

References · 42

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  2. 2016XGBoost: A Scalable Tree Boosting Systemcited by 5,120
  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. 2019A Survey on Bias and Fairness in Machine Learningcited by 1,911
  6. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
  7. 2018A Survey Of Methods For Explaining Black Box Modelscited by 970
  8. 2016The Mythos of Model Interpretabilitycited by 716
  9. 2021Interpretable Machine Learning: Fundamental Principles and 10 Grand Challengescited by 364
  10. 2017Methods for Interpreting and Understanding Deep Neural Networkscited by 342
  11. 2020Fairness in Machine Learningcited by 194
  12. 2018Abduction-Based Explanations for Machine Learning Modelscited by 159
30 more
  1. 2018A Symbolic Approach to Explaining Bayesian Network Classifierscited by 130
  2. 2020Reliable Post hoc Explanations: Modeling Uncertainty in Explainabilitycited by 125
  3. 2019Towards Explainable Artificial Intelligencecited by 106
  4. 2019Optimal Sparse Decision Treescited by 104
  5. 2018L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Datacited by 100
  6. 2020On the Tractability of SHAP Explanationscited by 92
  7. 2020Model Interpretability through the Lens of Computational Complexitycited by 75
  8. 2021On Explaining Random Forests with SATcited by 57
  9. 2020Explaining Naive Bayes and Other Linear Classifiers with Polynomial Time and Delaycited by 56
  10. 2021On Guaranteed Optimal Robust Explanations for NLP Modelscited by 54
  11. 2020On Explaining Decision Treescited by 49
  12. 2022Logic-Based Explainability in Machine Learningcited by 47
  13. 2022On Tackling Explanation Redundancy in Decision Treescited by 44
  14. 2021On the Computational Intelligibility of Boolean Classifierscited by 40
  15. 2021SAT-Based Rigorous Explanations for Decision Listscited by 40
  16. 2021Explanations for Monotonic Classifierscited by 39
  17. 2021On Efficiently Explaining Graph-Based Classifierscited by 37
  18. 2016Towards Verified Artificial Intelligencecited by 36
  19. 2022On Computing Probabilistic Explanations for Decision Treescited by 35
  20. 2019On Validating, Repairing and Refining Heuristic ML Explanationscited by 32
  21. 2021On the Complexity of SHAP-Score-Based Explanations: Tractability via Knowledge Compilation and Non-Approximability Resultscited by 32
  22. 2021Provably efficient, succinct, and precise explanationscited by 32
  23. 2023The Inadequacy of Shapley Values for Explainabilitycited by 30
  24. 2021Foundations of Symbolic Languages for Model Interpretabilitycited by 26
  25. 2022ASTERYX : A model-Agnostic SaT-basEd appRoach for sYmbolic and score-based eXplanationscited by 26
  26. 2022Eliminating The Impossible, Whatever Remains Must Be Truecited by 23
  27. 2022Feature Necessity & Relevancy in ML Classifier Explanationscited by 22
  28. 2021Rational Shapley Valuescited by 18
  29. 2021On Quantifying Literals in Boolean Logic and Its Applications to Explainable AIcited by 16
  30. 2021A unified logical framework for explanations in classifier systemscited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 4; 2024: 3; 2025: 2; 2026: 3.

12 papers.

  1. 2023Explainability is NOT a Gamecited by 23
  2. 2024Distance-Restricted Explanations: Theoretical Underpinnings & Efficient Implementationcited by 20
  3. 2023On Formal Feature Attribution and Its Approximationcited by 11
  4. 2024From SHAP Scores to Feature Importance Scorescited by 8
  5. 2023Refutation of Shapley Values for XAI -- Additional Evidencecited by 4
  6. 2026FAME: Formal Abstract Minimal Explanation for Neural Networkscited by 3
  7. 2024Logic-Based Explainability: Past, Present & Futurecited by 2
  8. 2023The Pros and Cons of Adversarial Robustnesscited by 1
  9. 2025Uncovering Bugs in Formal Explainers: A Case Study with PyXAIcited by 1
  10. 2025Efficient & Correct Predictive Equivalence for Decision Treescited by 0
  11. 2026Bridging AI and Clinical Reasoning: Abductive Explanations for Alignment on Critical Symptomscited by 0
  12. 2026Formal Abductive Explanations for Navigating Mental Health Help-Seeking and Diversity in Tech Workplacescited by 0