mlsanityData to 7 Oct 2026

Explainability is NOT a Game

arXiv 2307.07514 ↗First posted 27 Jun 2023cs.AI cs.LGcited by 23

Not on the map. Why?

Abstract (arXiv)

Explainable artificial intelligence (XAI) aims to help human decision-makers in understanding complex machine learning (ML) models. One of the hallmarks of XAI are measures of relative feature importance, which are theoretically justified through the use of Shapley values. This paper builds on recent work and offers a simple argument for why Shapley values can provide misleading measures of relative feature importance, by assigning more importance to features that are irrelevant for a prediction, and assigning less importance to features that are relevant for a prediction. The significance of these results is that they effectively challenge the many proposed uses of measures of relative feature importance in a fast-growing range of high-stakes application domains.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). Builds on 19 of its 45 references that are in the map. First posted on arXiv 27 Jun 2023.

Builds on

19 of 45 references.

References · 19

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  3. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  4. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
  5. 2020Problems with Shapley-value-based explanations as feature importance measurescited by 198
  6. 2018Abduction-Based Explanations for Machine Learning Modelscited by 159
  7. 2018A Symbolic Approach to Explaining Bayesian Network Classifierscited by 130
  8. 2020Reliable Post hoc Explanations: Modeling Uncertainty in Explainabilitycited by 125
  9. 2022Algorithms to estimate Shapley value feature attributionscited by 114
  10. 2018L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Datacited by 100
  11. 2020On the Tractability of SHAP Explanationscited by 92
  12. 2022Logic-Based Explainability in Machine Learningcited by 47
7 more
  1. 2022On Tackling Explanation Redundancy in Decision Treescited by 44
  2. 2019On Validating, Repairing and Refining Heuristic ML Explanationscited by 32
  3. 2021On the Complexity of SHAP-Score-Based Explanations: Tractability via Knowledge Compilation and Non-Approximability Resultscited by 32
  4. 2023The Inadequacy of Shapley Values for Explainabilitycited by 30
  5. 2021Rational Shapley Valuescited by 18
  6. 2023From Robustness to Explainability and Back Againcited by 14
  7. 2023Disproving XAI Myths with Formal Methods -- Initial Resultscited by 12

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 5; 2024: 5; 2025: 10; 2026: 3.

23 papers.

Sort:

  1. 2023Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directionscited by 123
  2. 2023Anytime Approximate Formal Feature Attributioncited by 9
  3. 2025SHAP Meets Tensor Networks: Provably Tractable Explanations with Parallelismcited by 8
  4. 2025Most General Explanations of Tree Ensembles (Extended Version)cited by 7
  5. 2024Formal Explanations for Neuro-Symbolic AIcited by 5
  6. 2023A Refutation of Shapley Values for Explainabilitycited by 4
  7. 2023Refutation of Shapley Values for XAI -- Additional Evidencecited by 4
  8. 2025Shapley Revisited: Tractable Responsibility Measures for Query Answerscited by 4
  9. 2024Logic-Based Explainability: Past, Present & Futurecited by 2
  10. 2024Understanding XAI Through the Philosopher's Lens: A Historical Perspectivecited by 2
  11. 2024A Shapley Value Estimation Speedup for Efficient Explainable Quantum AIcited by 2
  12. 2025Robust Explanations Through Uncertainty Decomposition: A Path to Trustworthier AIcited by 2
11 more
  1. 2023The Pros and Cons of Adversarial Robustnesscited by 1
  2. 2024Distributional Refinement Network: Distributional Forecasting via Deep Learningcited by 1
  3. 2025Uncovering Bugs in Formal Explainers: A Case Study with PyXAIcited by 1
  4. 2025Rigorous Feature Importance Scores based on Shapley Value and Banzhaf Indexcited by 0
  5. 2025SHAining on Process Mining: Explaining Event Log Characteristics Impact on Algorithmscited by 0
  6. 2025Feature Attribution in 5G Intrusion Detection: A Statistical vs. Logic-Based Comparisoncited by 0
  7. 2025Efficient & Correct Predictive Equivalence for Decision Treescited by 0
  8. 2025Leveraging Association Rules for Better Predictions and Better Explanationscited by 0
  9. 2026Bridging AI and Clinical Reasoning: Abductive Explanations for Alignment on Critical Symptomscited by 0
  10. 2026Shapley meets Rawls: an integrated framework for measuring and explaining unfairnesscited by 0
  11. 2026Towards Rigorous Explainability by Feature Attributioncited by 0