mlsanityData to 14 Oct 2026

The role of causality in explainable artificial intelligence

arXiv 2309.09901 ↗First posted 18 Sep 2023cs.AIcited by 17

Not on the map. Why?

Abstract (arXiv)

Causality and eXplainable Artificial Intelligence (XAI) have developed as separate fields in computer science, even though the underlying concepts of causation and explanation share common ancient roots. This is further enforced by the lack of review works jointly covering these two fields. In this paper, we investigate the literature to try to understand how and to what extent causality and XAI are intertwined. More precisely, we seek to uncover what kinds of relationships exist between the two concepts and how one can benefit from them, for instance, in building trust in AI systems. As a result, three main perspectives are identified. In the first one, the lack of causality is seen as one of the major limitations of current AI and XAI approaches, and the "optimal" form of explanations is investigated. The second is a pragmatic perspective and considers XAI as a tool to foster scientific exploration for causal inquiry, via the identification of pursue-worthy experimental manipulations. Finally, the third perspective supports the idea that causality is propaedeutic to XAI in three possible manners: exploiting concepts borrowed from causality to support or improve XAI, utilizing counterfactuals for explainability, and considering accessing a causal model as explaining itself. To complement our analysis, we also provide relevant software solutions used to automate causal tasks. We believe our work provides a unified view of the two fields of causality and XAI by highlighting potential domain bridges and uncovering possible limitations.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Builds on 38 of its 136 references that are in the map. First posted on arXiv 18 Sep 2023.

Builds on

38 of 136 references.

References · 38

  1. 2019Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AIcited by 1,552
  2. 2017Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPRcited by 1,089
  3. 2018A Survey Of Methods For Explaining Black Box Modelscited by 973
  4. 2016The Mythos of Model Interpretabilitycited by 721
  5. 2019Explaining Machine Learning Classifiers through Diverse Counterfactual Explanationscited by 614
  6. 2020Algorithmic Recourse: from Counterfactual Explanations to Interventionscited by 250
  7. 2018Techniques for Interpretable Machine Learningcited by 238
  8. 2019Feature relevance quantification in explainable AI: A causal problemcited by 167
  9. 2021Explainable artificial intelligence (XAI) in deep learning-based medical image analysiscited by 147
  10. 2020Interpretable Machine Learning -- A Brief History, State-of-the-Art and Challengescited by 120
  11. 2020Drug discovery with explainable artificial intelligencecited by 118
  12. 2020Causal Shapley Values: Exploiting Causal Knowledge to Explain Individual Predictions of Complex Modelscited by 107
26 more
  1. 2017Causal Structure Learningcited by 84
  2. 2022Learning and Evaluating Graph Neural Network Explanations based on Counterfactual and Factual Reasoningcited by 79
  3. 2020General Pitfalls of Model-Agnostic Interpretation Methods for Machine Learning Modelscited by 75
  4. 2018Theoretical Impediments to Machine Learning With Seven Sparks from the Causal Revolutioncited by 66
  5. 2021Counterfactuals and Causability in Explainable Artificial Intelligence: Theory, Algorithms, and Applicationscited by 59
  6. 2020Evaluating and Mitigating Bias in Image Classifiers: A Causal Perspective Using Counterfactualscited by 56
  7. 2021Explaining Black-Box Algorithms Using Probabilistic Contrastive Counterfactualscited by 55
  8. 2023Adversarial attacks and defenses in explainable artificial intelligence: A surveycited by 48
  9. 2021Local Explanations via Necessity and Sufficiency: Unifying Theory and Practicecited by 45
  10. 2019Explainable artificial intelligence model to predict acute critical illness from electronic health recordscited by 42
  11. 2021How Well do Feature Visualizations Support Causal Understanding of CNN Activations?cited by 28
  12. 2020Survey of explainable machine learning with visual and granular methods beyond quasi-explanationscited by 20
  13. 2023Causal Deep Learningcited by 20
  14. 2021Rational Shapley Valuescited by 18
  15. 2021Agree to Disagree: When Deep Learning Models With Identical Architectures Produce Distinct Explanationscited by 15
  16. 2020A multi-component framework for the analysis and design of explainable artificial intelligencecited by 14
  17. 2021Explanations for Occluded Imagescited by 14
  18. 2021Outcome-Explorer: A Causality Guided Interactive Visual Interface for Interpretable Algorithmic Decision Makingcited by 12
  19. 2023Causal reasoning in typical computer vision taskscited by 12
  20. 2022Machine Learning and Deep Learning -- A review for Ecologistscited by 11
  21. 2019Natural Language Generation Challenges for Explainable AIcited by 10
  22. 2023Counterfactual Formulation of Patient-Specific Root Causes of Diseasecited by 8
  23. 2022Benchmarking Instance-Centric Counterfactual Algorithms for XAI: From White Box to Black Boxcited by 7
  24. 2021An Interpretable Approach to Automated Severity Scoring in Pelvic Traumacited by 5
  25. 2017Why did the Robot Cross the Road? - Learning from Multi-Modal Sensor Data for Autonomous Road Crossingcited by 3
  26. 2021Scope and Sense of Explainability for AI-Systemscited by 2

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 3; 2025: 7; 2026: 6.

17 papers.

Sort:

By area:

  1. 2024Towards Compositional Interpretability for XAIcited by 12
  2. 2024Explain the Black Box for the Sake of Science: the Scientific Method in the Era of Generative Artificial Intelligencecited by 5
  3. 2023Survey on AI Ethics: A Socio-technical Perspectivecited by 4
  4. 2026Explainable AI: Learning from the Learnerscited by 4
  5. 2025Attribution Explanations for Deep Neural Networks: A Theoretical Perspectivecited by 2
  6. 2025GraphRAG-Causal: A novel graph-augmented framework for causal reasoning and annotation in newscited by 1
  7. 2025Chain-of-Image Generation: Toward Monitorable and Controllable Image Generationcited by 1
  8. 2026What is Missing? Explaining Neurons Activated by Absent Conceptscited by 1
  9. 2024Predicting Trust Dynamics with Dynamic SEM in Human-AI Cooperationcited by 0
  10. 2025Interpretable Neural System Dynamics: Combining Deep Learning with System Dynamics Modeling to Support Critical Applicationscited by 0
  11. 2025OpenAg: Democratizing Agricultural Intelligencecited by 0
  12. 2025Towards explainable decision support using hybrid neural models for logistic terminal automationcited by 0
5 more
  1. 2025Integrating a Causal Foundation Model into a Prescriptive Maintenance Framework for Optimising Production-Line OEEcited by 0
  2. 2026cc-Shapley: Measuring Multivariate Feature Importance Needs Causal Contextcited by 0
  3. 2026Position: Explainable AI is Causality in Disguisecited by 0
  4. 2026Hierarchical Causal Abduction: A Foundation Framework for Explainable Model Predictive Controlcited by 0
  5. 2026A Step Towards Inherently Interpretable Causal Machine Learning Models For Decision Supportcited by 0