mlsanityData to 7 Oct 2026

Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR

arXiv 1711.00399 ↗First posted 1 Nov 2017cs.AIcited by 1,086

Not on the map. Why?

Abstract (arXiv)

There has been much discussion of the right to explanation in the EU General Data Protection Regulation, and its existence, merits, and disadvantages. Implementing a right to explanation that opens the black box of algorithmic decision-making faces major legal and technical barriers. Explaining the functionality of complex algorithmic decision-making systems and their rationale in specific cases is a technically challenging problem. Some explanations may offer little meaningful information to data subjects, raising questions around their value. Explanations of automated decisions need not hinge on the general public understanding how algorithmic systems function. Even though such interpretability is of great importance and should be pursued, explanations can, in principle, be offered without opening the black box. Looking at explanations as a means to help a data subject act rather than merely understand, one could gauge the scope and content of explanations according to the specific goal or action they are intended to support. From the perspective of individuals affected by automated decision-making, we propose three aims for explanations: (1) to inform and help the individual understand why a particular decision was reached, (2) to provide grounds to contest the decision if the outcome is undesired, and (3) to understand what would need to change in order to receive a desired result in the future, based on the current decision-making model. We assess how each of these goals finds support in the GDPR. We suggest data controllers should offer a particular type of explanation, unconditional counterfactual explanations, to support these three aims. These counterfactual explanations describe the smallest change to the world that can be made to obtain a desirable outcome, or to arrive at the closest possible world, without needing to explain the internal logic of the system.

Key facts. Cited by 1,086 papers in the map (data through 7 Oct 2026). First posted on arXiv 1 Nov 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2020: 1; 2021: 141; 2022: 173; 2023: 186; 2024: 215; 2025: 179; 2026: 191.

1,086 papers.

Sort:

By area:

  1. 2021Deep Neural Networks and Tabular Data: A Surveycited by 489
  2. 2021Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Surveycited by 457
  3. 2021Trustworthy AI: From Principles to Practicescited by 206
  4. 2023Data-centric Artificial Intelligence: A Surveycited by 202
  5. 2021Causal Inference in Natural Language Processing: Estimation, Prediction, Interpretation and Beyondcited by 177
  6. 2022If Influence Functions are the Answer, Then What is the Question?cited by 142
  7. 2021Benchmarking and Survey of Explanation Methods for Black Box Modelscited by 136
  8. 2022OpenXAI: Towards a Transparent Evaluation of Model Explanationscited by 125
  9. 2021Human-Centered Explainable AI (XAI): From Algorithms to User Experiencescited by 123
  10. 2021Explaining in Style: Training a GAN to explain a classifier in StyleSpacecited by 122
  11. 2021What Do We Want From Explainable Artificial Intelligence (XAI)? -- A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Researchcited by 119
  12. 2021CF-GNNExplainer: Counterfactual Explanations for Graph Neural Networkscited by 118
38 more
  1. 2021Interpretable Deep Learning: Interpretation, Interpretability, Trustworthiness, and Beyondcited by 116
  2. 2021Counterfactual Explanations Can Be Manipulatedcited by 113
  3. 2023Regulating ChatGPT and other Large Generative AI Modelscited by 102
  4. 2021Towards Robust and Reliable Algorithmic Recoursecited by 101
  5. 2022Diffusion Visual Counterfactual Explanationscited by 96
  6. 2021Trustworthy AI: A Computational Perspectivecited by 93
  7. 2023Can Large Language Models Explain Themselves? A Study of LLM-Generated Self-Explanationscited by 90
  8. 2022Diffusion Causal Models for Counterfactual Estimationcited by 87
  9. 2021CARLA: A Python Library to Benchmark Algorithmic Recourse and Counterfactual Explanation Algorithmscited by 85
  10. 2022Towards Human-centered Explainable AI: A Survey of User Studies for Model Explanationscited by 84
  11. 2021If Only We Had Better Counterfactual Explanations: Five Key Deficits to Rectify in the Evaluation of Counterfactual XAI Techniquescited by 82
  12. 2024Robust agents learn causal world modelscited by 81
  13. 2021Explainability of deep vision-based autonomous driving systems: Review and challengescited by 80
  14. 2021Explanations in Autonomous Driving: A Surveycited by 80
  15. 2022Diffusion Models for Counterfactual Explanationscited by 79
  16. 2022Which Explanation Should I Choose? A Function Approximation Perspective to Characterizing Post Hoc Explanationscited by 77
  17. 2025Interactive Debugging and Steering of Multi-Agent AI Systemscited by 68
  18. 2021Beyond Expertise and Roles: A Framework to Characterize the Stakeholders of Interpretable Machine Learning and their Needscited by 64
  19. 2021NICE: An Algorithm for Nearest Instance Counterfactual Explanationscited by 62
  20. 2022Concept Embedding Models: Beyond the Accuracy-Explainability Trade-Offcited by 61
  21. 2021Counterfactual Explainable Recommendationcited by 60
  22. 2021Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applicationscited by 59
  23. 2022From Shapley Values to Generalized Additive Models and backcited by 59
  24. 2021Understanding the Effect of Out-of-distribution Examples and Interactive Explanations on Human-AI Decision Makingcited by 58
  25. 2022GraphFramEx: Towards Systematic Evaluation of Explainability Methods for Graph Neural Networkscited by 57
  26. 2021Socially Responsible AI Algorithms: Issues, Purposes, and Challengescited by 56
  27. 2021On the Adversarial Robustness of Causal Algorithmic Recoursecited by 56
  28. 2023Interpretable Neural-Symbolic Concept Reasoningcited by 56
  29. 2021Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactualscited by 55
  30. 2021Meaningfully Debugging Model Mistakes using Conceptual Counterfactual Explanationscited by 53
  31. 2022Post-Hoc Explanations Fail to Achieve their Purpose in Adversarial Contextscited by 53
  32. 2023High Fidelity Image Counterfactuals with Probabilistic Causal Modelscited by 53
  33. 2021Exploring Counterfactual Explanations Through the Lens of Adversarial Examples: A Theoretical and Empirical Analysiscited by 52
  34. 2022Rethinking Explainability as a Dialogue: A Practitioner's Perspectivecited by 52
  35. 2022Leveraging Explanations in Interactive Machine Learning: An Overviewcited by 52
  36. 2022Robust Counterfactual Explanations for Tree-Based Ensemblescited by 49
  37. 2022CLEAR: Generative Counterfactual Explanations on Graphscited by 48
  38. 2021Towards the Unification and Robustness of Perturbation and Gradient Based Explanationscited by 47

50 most cited of 1,086 All 1,086 (JSON)