mlsanityData to 14 Oct 2026

Contrastive Explanation: A Structural-Model Approach

arXiv 1811.03163 ↗First posted 7 Nov 2018cs.AIcited by 65

Not on the map. Why?

Abstract (arXiv)

This paper presents a model of contrastive explanation using structural casual models. The topic of causal explanation in artificial intelligence has gathered interest in recent years as researchers and practitioners aim to increase trust and understanding of intelligent decision-making. While different sub-fields of artificial intelligence have looked into this problem with a sub-field-specific view, there are few models that aim to capture explanation more generally. One general model is based on structural causal models. It defines an explanation as a fact that, if found to be true, would constitute an actual cause of a specific event. However, research in philosophy and social sciences shows that explanations are contrastive: that is, when people ask for an explanation of an event -- the fact -- they (sometimes implicitly) are asking for an explanation relative to some contrast case; that is, "Why P rather than Q?". In this paper, we extend the structural causal model approach to define two complementary notions of contrastive explanation, and demonstrate them on two classical problems in artificial intelligence: classification and planning. We believe that this model can help researchers in subfields of artificial intelligence to better understand contrastive explanation.

Key facts. Cited by 65 papers in the map (data through 14 Oct 2026). First posted on arXiv 7 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 12; 2022: 12; 2023: 16; 2024: 10; 2025: 8; 2026: 7.

65 papers.

Sort:

By area:

  1. 2023Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanationscited by 85
  2. 2021Contrastive Explanations for Model Interpretabilitycited by 75
  3. 2023Explainable AI is Dead, Long Live Explainable AI! Hypothesis-driven decision supportcited by 66
  4. 2021Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Predictioncited by 59
  5. 2022Do People Engage Cognitively with AI? Impact of AI Assistance on Incidental Learningcited by 53
  6. 2021Prompting Contrastive Explanations for Commonsense Reasoning Taskscited by 45
  7. 2023Knowing About Knowing: An Illusion of Human Competence Can Hinder Appropriate Reliance on AI Systemscited by 41
  8. 2022A Survey on Explainable Anomaly Detectioncited by 39
  9. 2022Sensible AI: Re-imagining Interpretability and Explainability using Sensemaking Theorycited by 32
  10. 2021Towards Relatable Explainable AI with the Perceptual Processcited by 27
  11. 2021Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Surveycited by 24
  12. 2022Counterfactual Plans under Distributional Ambiguitycited by 19
38 more
  1. 2021From Human Explanation to Model Interpretability: A Framework Based on Weight of Evidencecited by 17
  2. 2021Contrastive Explanations of Plans Through Model Restrictionscited by 16
  3. 2021A unified logical framework for explanations in classifier systemscited by 15
  4. 2022Diagnosing AI Explanation Methods with Folk Concepts of Behaviorcited by 15
  5. 2021Directive Explanations for Actionable Explainability in Machine Learning Applicationscited by 14
  6. 2024Contrastive Explanations That Anticipate Human Misconceptions Can Improve Human Decision-Making Skillscited by 14
  7. 2023Natural Example-Based Explainability: a Surveycited by 13
  8. 2021Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbationcited by 11
  9. 2022A Framework for Inherently Interpretable Optimization Modelscited by 8
  10. 2023The Utility of "Even if..." Semifactual Explanation to Optimise Positive Outcomescited by 8
  11. 2022Alterfactual Explanations -- The Relevance of Irrelevance for Explaining AI Systemscited by 7
  12. 2022A general-purpose method for applying Explainable AI for Anomaly Detectioncited by 7
  13. 2024Towards a Framework for Evaluating Explanations in Automated Fact Verificationcited by 7
  14. 2021Contrastive Explanations for Argumentation-Based Conclusionscited by 4
  15. 2022Improving Model Understanding and Trust with Counterfactual Explanations of Model Confidencecited by 4
  16. 2023Explaining Model Confidence Using Counterfactualscited by 4
  17. 2023Contrastive Explanations of Centralized Multi-agent Optimization Solutionscited by 4
  18. 2023Forms of Understanding for XAI-Explanationscited by 4
  19. 2024Explaining Decisions of Agents in Mixed-Motive Gamescited by 4
  20. 2024ConPro: Learning Severity Representation for Medical Images using Contrastive Learning and Preference Optimizationcited by 3
  21. 2024Relevant Irrelevance: Generating Alterfactual Explanations for Image Classifierscited by 3
  22. 2025A moving target in AI-assisted decision-making: Dataset shift, model updating, and the problem of update opacitycited by 3
  23. 2022Summarising and Comparing Agent Dynamics with Contrastive Spatiotemporal Abstractioncited by 2
  24. 2023Towards Reconciling Usability and Usefulness of Explainable AI Methodologiescited by 2
  25. 2023Attribution-Scores and Causal Counterfactuals as Explanations in Artificial Intelligencecited by 2
  26. 2023A Framework for Data-Driven Explainability in Mathematical Optimizationcited by 2
  27. 2023Explainable AI for clinical risk prediction: a survey of concepts, methods, and modalitiescited by 2
  28. 2024Axe the X in XAI: A Plea for Understandable AIcited by 2
  29. 2024COIN: Counterfactual inpainting for weakly supervised semantic segmentation for medical imagescited by 2
  30. 2024Explaining an Agent's Future Beliefs through Temporally Decomposing Future Reward Estimatorscited by 2
  31. 2025Comparative Explanations: Explanation Guided Decision Making for Human-in-the-Loop Preference Selectioncited by 2
  32. 2025Robust Explanations Through Uncertainty Decomposition: A Path to Trustworthier AIcited by 2
  33. 2021LEx: A Framework for Operationalising Layers of Machine Learning Explanationscited by 1
  34. 2022Scientific Explanation and Natural Language: A Unified Epistemological-Linguistic Perspective for Explainable AIcited by 1
  35. 2022Understanding a Robot's Guiding Ethical Principles via Automatically Generated Explanationscited by 1
  36. 2024When a Relation Tells More Than a Concept: Exploring and Evaluating Classifier Decisions with CoReXcited by 1
  37. 2025Interactivity x Explainability: Toward Understanding How Interactivity Can Improve Computer Vision Explanationscited by 1
  38. 2025Searching for Actual Causes: Approximate Algorithms with Adjustable Precisioncited by 1

50 most cited of 65 All 65 (JSON)