mlsanityData to 7 Oct 2026

Rethinking Explainable Machine Learning as Applied Statistics

arXiv 2402.02870 ↗First posted 5 Feb 2024cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

In the rapidly growing literature on explanation algorithms, it often remains unclear what precisely these algorithms are for and how they should be used. In this position paper, we argue for a novel and pragmatic perspective: Explainable machine learning needs to recognize its parallels with applied statistics. Concretely, explanations are statistics of high-dimensional functions, and we should think about them analogously to traditional statistical quantities. Among others, this implies that we must think carefully about the matter of interpretation, or how the explanations relate to intuitive questions that humans have about the world. The fact that this is scarcely being discussed in research papers is one of the main drawbacks of the current literature. Moving forward, the analogy between explainable machine learning and applied statistics suggests fruitful ways for how research practices can be improved.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 54 of its 125 references that are in the map. First posted on arXiv 5 Feb 2024.

Builds on

54 of 125 references.

References · 54

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  3. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  6. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  7. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
  8. 2018Sanity Checks for Saliency Mapscited by 1,149
  9. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  10. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 936
  11. 2023Progress measures for grokking via mechanistic interpretabilitycited by 822
  12. 2016Distribution-Free Predictive Inference For Regressioncited by 657
38 more
  1. 2018Explaining Explanations: An Overview of Interpretability of Machine Learningcited by 508
  2. 2018A Benchmark for Interpretability Methods in Deep Neural Networkscited by 467
  3. 2019Fooling LIME and SHAP: Adversarial Attacks on Post hoc Explanation Methodscited by 440
  4. 2020Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performancecited by 396
  5. 2018All Models are Wrong, but Many are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneouslycited by 364
  6. 2023Finding Neurons in a Haystack: Case Studies with Sparse Probingcited by 328
  7. 2020Questioning the AI: Informing Design Practices for Explainable AI User Experiencescited by 251
  8. 2020Explaining by Removing: A Unified Framework for Model Explanationcited by 218
  9. 2020Problems with Shapley-value-based explanations as feature importance measurescited by 198
  10. 2022Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyondcited by 171
  11. 2022The Disagreement Problem in Explainable Machine Learning: A Practitioner's Perspectivecited by 156
  12. 2020Debugging Tests for Model Explanationscited by 146
  13. 2018Explaining Explanations in AIcited by 136
  14. 2021Expanding Explainability: Towards Social Transparency in AI systemscited by 124
  15. 2021FastSHAP: Real-Time Shapley Value Estimationcited by 123
  16. 2021Human-Centered Explainable AI (XAI): From Algorithms to User Experiencescited by 123
  17. 2020Explaining the Explainer: A First Theoretical Analysis of LIMEcited by 89
  18. 2021CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithmscited by 85
  19. 2022Impossibility Theorems for Feature Attributioncited by 78
  20. 2020General Pitfalls of Model-Agnostic Interpretation Methods for Machine Learning Modelscited by 74
  21. 2020Fairwashing Explanations with Off-Manifold Detergentcited by 71
  22. 2022From Shapley Values to Generalized Additive Models and backcited by 59
  23. 2022Post hoc Explanations may be Ineffective for Detecting Unknown Spurious Correlationcited by 59
  24. 2022Post-Hoc Explanations Fail to Achieve their Purpose in Adversarial Contextscited by 53
  25. 2022Rethinking Explainability as a Dialogue: A Practitioner's Perspectivecited by 52
  26. 2020Robust and Stable Black Box Explanationscited by 47
  27. 2021Towards the Unification and Robustness of Perturbation and Gradient Based Explanationscited by 47
  28. 2022Learning to Estimate Shapley Values with Vision Transformerscited by 44
  29. 2023Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZerocited by 41
  30. 2023Don't trust your eyes: on the (un)reliability of feature visualizationscited by 32
  31. 2021Interpretable Data-Based Explanations for Fairness Debuggingcited by 30
  32. 2023The Rashomon Importance Distribution: Getting RID of Unstable, Single Model-based Variable Importancecited by 29
  33. 2020Enforcing Interpretability and its Statistical Impacts: Trade-offs between Accuracy and Interpretabilitycited by 24
  34. 2023Dear XAI Community, We Need to Talk! Fundamental Misconceptions in Current XAI Researchcited by 22
  35. 2023Statistical Inference for Fairness Auditingcited by 19
  36. 2020Floodgate: inference for model-free variable importancecited by 15
  37. 2021Decorrelated Variable Importancecited by 12
  38. 2023A Framework for Interpretability in Machine Learning for Medical Imagingcited by 9

50 most cited of 54 All 54 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 1; 2025: 3; 2026: 4.

8 papers.

  1. 2025Interpretable Machine Learning in Physics: A Reviewcited by 11
  2. 2024A Fresh Look at Sanity Checks for Saliency Mapscited by 8
  3. 2025Informative Post-Hoc Explanations Only Exist for Simple Functionscited by 2
  4. 2026The Age of AI Agents Demands A New Scientific Paradigm To Sustain Trustworthy Sciencecited by 1
  5. 2025Unifying Post-hoc Explanations of Knowledge Graph Completionscited by 0
  6. 2026Towards Rigorous Explainability by Feature Attributioncited by 0
  7. 2026How Complexity Contributes to Learning Opacity in Machine Learningcited by 0
  8. 2026An Investigation of the NeurIPS and ICML 2025 Position Trackscited by 0