# The Inadequacy of Shapley Values for Explainability

arXiv: https://arxiv.org/abs/2302.08160 · HTML: https://mlsanity.com/paper/2302.08160/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 39 of its 108 references that are in the map.
- First posted on arXiv 16 Feb 2023.

## Builds on (most cited first, 30 of 39)

- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [The many Shapley values for model explanation](https://mlsanity.com/paper/1908.08474/) (2019)
- [Problems with Shapley-value-based explanations as feature importance measures](https://mlsanity.com/paper/2002.11097/) (2020)
- [Abduction-Based Explanations for Machine Learning Models](https://mlsanity.com/paper/1811.10656/) (2018)
- [Improving KernelSHAP: Practical Shapley Value Estimation via Linear Regression](https://mlsanity.com/paper/2012.01536/) (2020)
- [PMLB: A Large Benchmark Suite for Machine Learning Evaluation and Comparison](https://mlsanity.com/paper/1703.00512/) (2017)
- [Reliable Post hoc Explanations: Modeling Uncertainty in Explainability](https://mlsanity.com/paper/2008.05030/) (2020)
- [FastSHAP: Real-Time Shapley Value Estimation](https://mlsanity.com/paper/2107.07436/) (2021)
- [Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainability](https://mlsanity.com/paper/1910.06358/) (2019)
- [L-Shapley and C-Shapley: Efficient Model Interpretation for Structured Data](https://mlsanity.com/paper/1808.02610/) (2018)
- [On The Reasons Behind Decisions](https://mlsanity.com/paper/2002.09284/) (2020)
- [The Shapley Value in Machine Learning](https://mlsanity.com/paper/2202.05594/) (2022)
- [On the Tractability of SHAP Explanations](https://mlsanity.com/paper/2009.08634/) (2020)
- [Shapley explainability on the data manifold](https://mlsanity.com/paper/2006.01272/) (2020)
- [Model Interpretability through the Lens of Computational Complexity](https://mlsanity.com/paper/2010.12265/) (2020)
- [Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same End](https://mlsanity.com/paper/2011.04917/) (2020)
- [Explaining Naive Bayes and Other Linear Classifiers with Polynomial Time and Delay](https://mlsanity.com/paper/2008.05803/) (2020)
- [On Explaining Random Forests with SAT](https://mlsanity.com/paper/2105.10278/) (2021)
- [Shapley values for feature selection: The good, the bad, and the axioms](https://mlsanity.com/paper/2102.10936/) (2021)
- [On Guaranteed Optimal Robust Explanations for NLP Models](https://mlsanity.com/paper/2105.03640/) (2021)
- [Logic-Based Explainability in Machine Learning](https://mlsanity.com/paper/2211.00541/) (2022)
- [Local Explanations via Necessity and Sufficiency: Unifying Theory and Practice](https://mlsanity.com/paper/2103.14651/) (2021)
- [On Tackling Explanation Redundancy in Decision Trees](https://mlsanity.com/paper/2205.09971/) (2022)
- [On the Computational Intelligibility of Boolean Classifiers](https://mlsanity.com/paper/2104.06172/) (2021)
- [SAT-Based Rigorous Explanations for Decision Lists](https://mlsanity.com/paper/2105.06782/) (2021)
- [Explanations for Monotonic Classifiers](https://mlsanity.com/paper/2106.00154/) (2021)
- [On Efficiently Explaining Graph-Based Classifiers](https://mlsanity.com/paper/2106.01350/) (2021)

## Built on by (most cited first, 30 of 31)

- [Explaining Predictive Uncertainty with Information Theoretic Shapley Values](https://mlsanity.com/paper/2306.05724/) (2023)
- [Explainability is NOT a Game](https://mlsanity.com/paper/2307.07514/) (2023)
- [Disproving XAI Myths with Formal Methods -- Initial Results](https://mlsanity.com/paper/2306.01744/) (2023)
- [On Formal Feature Attribution and Its Approximation](https://mlsanity.com/paper/2307.03380/) (2023)
- [Axiomatic Aggregations of Abductive Explanations](https://mlsanity.com/paper/2310.03131/) (2023)
- [Anytime Approximate Formal Feature Attribution](https://mlsanity.com/paper/2312.06973/) (2023)
- [From SHAP Scores to Feature Importance Scores](https://mlsanity.com/paper/2405.11766/) (2024)
- [Auditing Local Explanations is Hard](https://mlsanity.com/paper/2407.13281/) (2024)
- [Formal Explanations for Neuro-Symbolic AI](https://mlsanity.com/paper/2410.14219/) (2024)
- [Explaining Exchange Rate Forecasts with Macroeconomic Fundamentals Using Interpretive Machine Learning](https://mlsanity.com/paper/2303.16149/) (2023)
- [X Hacking: The Threat of Misguided AutoML](https://mlsanity.com/paper/2401.08513/) (2024)
- [Causality from Bottom to Top: A Survey](https://mlsanity.com/paper/2403.11219/) (2024)
- [A Refutation of Shapley Values for Explainability](https://mlsanity.com/paper/2309.03041/) (2023)
- [Refutation of Shapley Values for XAI -- Additional Evidence](https://mlsanity.com/paper/2310.00416/) (2023)
- [A Uniform Language to Explain Decision Trees](https://mlsanity.com/paper/2310.11636/) (2023)
- [Logic-Based Explainability: Past, Present & Future](https://mlsanity.com/paper/2406.11873/) (2024)
- [SHAP scores fail pervasively even when Lipschitz succeeds](https://mlsanity.com/paper/2412.13866/) (2024)
- [Self-Reinforcement Attention Mechanism For Tabular Learning](https://mlsanity.com/paper/2305.11684/) (2023)
- [Error Analysis of Shapley Value-Based Model Explanations: An Informative Perspective](https://mlsanity.com/paper/2404.13522/) (2024)
- [Stronger Baseline Models -- A Key Requirement for Aligning Machine Learning Research with Clinical Utility](https://mlsanity.com/paper/2409.12116/) (2024)
- [Explaining the Unexplained: Revealing Hidden Correlations for Better Interpretability](https://mlsanity.com/paper/2412.01365/) (2024)
- [The Explanation Game -- Rekindled (Extended Version)](https://mlsanity.com/paper/2501.11429/) (2025)
- [Feature Relevancy, Necessity and Usefulness: Complexity and Algorithms](https://mlsanity.com/paper/2505.09640/) (2025)
- [What's meant by explainable model: A Scoping Review](https://mlsanity.com/paper/2307.09673/) (2023)
- [Unifying Interpretability and Explainability for Alzheimer's Disease Progression Prediction](https://mlsanity.com/paper/2406.07777/) (2024)
- [Feature-Guided Neighbor Selection for Non-Expert Evaluation of Model Predictions](https://mlsanity.com/paper/2507.06029/) (2025)
- [Towards Rigorous Explainability by Feature Attribution](https://mlsanity.com/paper/2604.15898/) (2026)
- [We Need Explanation Cards to Connect Explanation Algorithms to the Real World](https://mlsanity.com/paper/2606.16786/) (2026)
- [Beyond Shapley: Efficient Computation of Asymmetric Shapley Values](https://mlsanity.com/paper/2606.25103/) (2026)
- [X-WAD: eXplainable Web Anomaly Detection](https://mlsanity.com/paper/2608.27172/) (2026)

## Abstract (arXiv)

This paper develops a rigorous argument for why the use of Shapley values in explainable AI (XAI) will necessarily yield provably misleading information about the relative importance of features for predictions. Concretely, this paper demonstrates that there exist classifiers, and associated predictions, for which the relative importance of features determined by the Shapley values will incorrectly assign more importance to features that are provably irrelevant for the prediction, and less importance to features that are provably relevant for the prediction. The paper also argues that, given recent complexity results, the existence of efficient algorithms for the computation of rigorous feature attribution values in the case of some restricted classes of classifiers should be deemed unlikely at best.