mlsanityData to 7 Oct 2026

If Only We Had Better Counterfactual Explanations: Five Key Deficits to Rectify in the Evaluation of Counterfactual XAI Techniques

arXiv 2103.01035 ↗First posted 26 Feb 2021cs.LG cs.AIcited by 82

Not on the map. Why?

Abstract (arXiv)

In recent years, there has been an explosion of AI research on counterfactual explanations as a solution to the problem of eXplainable AI (XAI). These explanations seem to offer technical, psychological and legal benefits over other explanation techniques. We survey 100 distinct counterfactual explanation methods reported in the literature. This survey addresses the extent to which these methods have been adequately evaluated, both psychologically and computationally, and quantifies the shortfalls occurring. For instance, only 21% of these methods have been user tested. Five key deficits in the evaluation of these methods are detailed and a roadmap, with standardised benchmark evaluations, is proposed to resolve the issues arising; issues, that currently effectively block scientific progress in this field.

Key facts. Cited by 82 papers in the map (data through 7 Oct 2026). Builds on 83 of its 167 references that are in the map. First posted on arXiv 26 Feb 2021.

Builds on

83 of 167 references.

References · 83

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  2. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  3. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  4. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,400
  5. 2017Explanation in Artificial Intelligence: Insights from the Social Sciencescited by 1,201
  6. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,086
  7. 2016The Mythos of Model Interpretabilitycited by 716
  8. 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 612
  9. 2020Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performancecited by 396
  10. 2018Actionable Recourse in Linear Classificationcited by 327
  11. 2019Counterfactual Visual Explanationscited by 312
  12. 2018Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negativescited by 261
38 more
  1. 2018Metrics for Explainable AI: Challenges and Prospectscited by 257
  2. 2018Manipulating and Measuring Model Interpretabilitycited by 256
  3. 2020Algorithmic Recourse: from Counterfactual Explanations to Interventionscited by 250
  4. 2019FACE: Feasible and Actionable Counterfactual Explanationscited by 232
  5. 2019Interpretable Counterfactual Explanations Guided by Prototypescited by 223
  6. 2019Explainable Machine Learning in Deploymentcited by 210
  7. 2019The What-If Tool: Interactive Probing of Machine Learning Modelscited by 207
  8. 2019Model-Agnostic Counterfactual Explanations for Consequential Decisionscited by 204
  9. 2018Local Rule-Based Explanations of Black Box Decision Systemscited by 165
  10. 2018On Human Predictions with Explanations and Predictions of Machine Learning Models: A Case Study on Deception Detectioncited by 159
  11. 2020Multi-Objective Counterfactual Explanationscited by 157
  12. 2019Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifierscited by 143
  13. 2020Algorithmic recourse under imperfect causal knowledge: a probabilistic approachcited by 139
  14. 2020Proxy Tasks and Subjective Measures Can Be Misleading in Evaluating Explainable AI Systemscited by 138
  15. 2018Explaining Explanations in AIcited by 136
  16. 2019Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systemscited by 128
  17. 2020A survey of algorithmic recourse: definitions, formulations, solutions, and prospectscited by 118
  18. 2019The Hidden Assumptions Behind Counterfactual Explanations and Principal Reasonscited by 115
  19. 2019Efficient Search for Diverse Coherent Explanationscited by 111
  20. 2019"How do I fool you?": Manipulating User Trust via Misleading Black Box Explanationscited by 111
  21. 2019The Dangers of Post-hoc Interpretability: Unjustified Counterfactual Explanationscited by 97
  22. 2018'It's Reducing a Human Being to a Percentage'; Perceptions of Justice in Algorithmic Decisionscited by 91
  23. 2017Explainable AI: Beware of Inmates Running the Asylum Or: How I Learnt to Stop Worrying and Love the Social and Behavioural Sciencescited by 84
  24. 2020Good Counterfactuals and Where to Find Them: A Case-Based Technique for Generating Counterfactuals for Explainable AI (XAI)cited by 79
  25. 2017Interpretable Predictions of Tree-based Ensembles via Actionable Feature Tweakingcited by 76
  26. 2019Explanation by Progressive Exaggerationcited by 76
  27. 2020Generate Your Counterfactuals: Towards Controlled Counterfactual Generation for Textcited by 75
  28. 2020On Counterfactual Explanations under Predictive Multiplicitycited by 73
  29. 2020Towards Unifying Feature Attribution and Counterfactual Explanations: Different Means to the Same Endcited by 66
  30. 2020Instance-based Counterfactual Explanations for Time Series Classificationcited by 64
  31. 2019Explanation in Human-AI Systems: A Literature Meta-Review, Synopsis of Key Ideas and Publications, and Bibliography for Explainable AIcited by 63
  32. 2020On Generating Plausible Counterfactual and Semi-Factual Explanations for Deep Learningcited by 60
  33. 2019Counterfactual Risk Assessments, Evaluation, and Fairnesscited by 59
  34. 2020Towards falsifiable interpretability researchcited by 53
  35. 2020SCOUT: Self-aware Discriminant Counterfactual Explanationscited by 52
  36. 2017Inverse Classification for Comparison-based Interpretability in Machine Learningcited by 49
  37. 2019Measurable Counterfactual Local Explanations for Any Classifiercited by 48
  38. 2020Counterfactual Fairness with Disentangled Causal Effect Variational Autoencodercited by 45

50 most cited of 83 All 83 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 15; 2023: 15; 2024: 22; 2025: 10; 2026: 8.

82 papers.

Sort:

By area:

  1. 2023Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directionscited by 123
  2. 2021A Comprehensive Taxonomy for Explainable Artificial Intelligence: A Systematic Survey of Surveys on Methods and Conceptscited by 90
  3. 2021NICE: An Algorithm for Nearest Instance Counterfactual Explanationscited by 62
  4. 2023Scientific Fact-Checking: A Survey of Resources and Approachescited by 53
  5. 2021Counterfactual Shapley Additive Explanationscited by 22
  6. 2022Attribution-based Explanations that Provide Recourse Cannot be Robustcited by 20
  7. 2023Even if Explanations: Prior Work, Desiderata & Benchmarks for Semi-Factual XAIcited by 20
  8. 2021A Framework and Benchmarking Study for Counterfactual Generating Methods on Tabular Datacited by 19
  9. 2023GANterfactual-RL: Understanding Reinforcement Learning Agents' Strategies through Visual Counterfactual Explanationscited by 17
  10. 2021Uncertainty Estimation and Out-of-Distribution Detection for Counterfactual Explanations: Pitfalls and Solutionscited by 16
  11. 2022Features of Explainability: How users understand counterfactual and causal explanations for categorical and continuous features in XAIcited by 16
  12. 2021An Objective Metric for Explainable AI: How and Why to Estimate the Degree of Explainabilitycited by 15
38 more
  1. 2023Natural Example-Based Explainability: a Surveycited by 13
  2. 2022Counterfactual Explanations for Misclassified Images: How Human and Machine Explanations Differcited by 12
  3. 2022Human-Centric Artificial Intelligence Architecture for Industry 5.0 Applicationscited by 11
  4. 2022Keep Your Friends Close and Your Counterfactuals Closer: Improved Learning From Closest Rather Than Plausible Counterfactual Explanations in an Abstract Settingcited by 11
  5. 2024Counterfactual Explanations with Probabilistic Guarantees on their Robustness to Model Changecited by 10
  6. 2022Let's Go to the Alien Zoo: Introducing an Experimental Framework to Study Usability of Counterfactual Explanations for Machine Learningcited by 9
  7. 2022Shapelet-Based Counterfactual Explanations for Multivariate Time Seriescited by 9
  8. 2023GAM Coach: Towards Interactive and User-centered Algorithmic Recoursecited by 9
  9. 2023Explaining Groups of Instances Counterfactually for XAI: A Use Case, Algorithm and User Study for Group-Counterfactualscited by 9
  10. 2021A Survey on Methods and Metrics for the Assessment of Explainability under the Proposed AI Actcited by 8
  11. 2021Solving the Class Imbalance Problem Using a Counterfactual Method for Data Augmentationcited by 8
  12. 2022Ask to Know More: Generating Counterfactual Explanations for Fake Claimscited by 8
  13. 2022Explaining Classifications to Non Experts: An XAI User Study of Post Hoc Explanations for a Classifier When People Lack Expertisecited by 8
  14. 2024Evaluating Explanations Through LLMs: Beyond Traditional User Studiescited by 8
  15. 2024Towards Unifying Evaluation of Counterfactual Explanations: Leveraging Large Language Models for Human-Centric Assessmentscited by 8
  16. 2022Benchmarking Instance-Centric Counterfactual Algorithms for XAI: From White Box to Black Boxcited by 7
  17. 2022Alterfactual Explanations -- The Relevance of Irrelevance for Explaining AI Systemscited by 7
  18. 2021DeDUCE: Generating Counterfactual Explanations Efficientlycited by 6
  19. 2022FASTER-CE: Fast, Sparse, Transparent, and Robust Counterfactual Explanationscited by 6
  20. 2023Counterfactuals of Counterfactuals: a back-translation-inspired approach to analyse counterfactual editorscited by 6
  21. 2024Why do explanations fail? A typology and discussion on failures in XAIcited by 6
  22. 2025RobustX: Robust Counterfactual Explanations Made Easycited by 6
  23. 2023Navigating Explanatory Multiverse Through Counterfactual Path Geometrycited by 5
  24. 2024Even-Ifs From If-Onlys: Are the Best Semi-Factual Explanations Found Using Counterfactuals As Guides?cited by 5
  25. 2024CountARFactuals -- Generating plausible model-agnostic counterfactual explanations with adversarial random forestscited by 5
  26. 2024Unifying Perspectives: Plausible Counterfactual Explanations on Global, Group-wise, and Local Levelscited by 5
  27. 2024Use of What-if Scenarios to Help Explain Artificial Intelligence Models for Neonatal Healthcited by 5
  28. 2024A Comparative Analysis of Counterfactual Explanation Methods for Text Classifierscited by 4
  29. 2026What-If Explanations Over Time: Counterfactuals for Time Series Classificationcited by 4
  30. 2021Twin Systems for DeepCBR: A Menagerie of Deep Learning and Case-Based Reasoning Pairings for Explanation and Data Augmentationcited by 3
  31. 2021An exact counterfactual-example-based approach to tree-ensemble models interpretabilitycited by 3
  32. 2024PUPAE: Intuitive and Actionable Explanations for Time Series Anomaliescited by 3
  33. 2024Relevant Irrelevance: Generating Alterfactual Explanations for Image Classifierscited by 3
  34. 2024Reassessing Evaluation Functions in Algorithmic Recourse: An Empirical Study from a Human-Centered Perspectivecited by 3
  35. 2021Handling Climate Change Using Counterfactuals: Using Counterfactuals in Data Augmentation to Predict Crop Growth in an Uncertain Climate Futurecited by 2
  36. 2023Reason to explain: Interactive contrastive explanations (REASONX)cited by 2
  37. 2024People Attribute Purpose to Autonomous Vehicles When Explaining Their Behavior: Insights from Cognitive Science for Explainable AIcited by 2
  38. 2024Explainable Interface for Human-Autonomy Teaming: A Surveycited by 2

50 most cited of 82 All 82 (JSON)