# Contrastive Explanation: A Structural-Model Approach

arXiv: https://arxiv.org/abs/1811.03163 · HTML: https://mlsanity.com/paper/1811.03163/

## Key facts

- Cited by 66 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Nov 2018.

## Built on by (most cited first, 30 of 66)

- [Do Models Explain Themselves? Counterfactual Simulatability of Natural Language Explanations](https://mlsanity.com/paper/2307.08678/) (2023)
- [Contrastive Explanations for Model Interpretability](https://mlsanity.com/paper/2103.01378/) (2021)
- [Explainable AI is Dead, Long Live Explainable AI! Hypothesis-driven decision support](https://mlsanity.com/paper/2302.12389/) (2023)
- [Counterfactual Interventions Reveal the Causal Effect of Relative Clause Representations on Agreement Prediction](https://mlsanity.com/paper/2105.06965/) (2021)
- [Do People Engage Cognitively with AI? Impact of AI Assistance on Incidental Learning](https://mlsanity.com/paper/2202.05402/) (2022)
- [Prompting Contrastive Explanations for Commonsense Reasoning Tasks](https://mlsanity.com/paper/2106.06823/) (2021)
- [Knowing About Knowing: An Illusion of Human Competence Can Hinder Appropriate Reliance on AI Systems](https://mlsanity.com/paper/2301.11333/) (2023)
- [A Survey on Explainable Anomaly Detection](https://mlsanity.com/paper/2210.06959/) (2022)
- [Sensible AI: Re-imagining Interpretability and Explainability using Sensemaking Theory](https://mlsanity.com/paper/2205.05057/) (2022)
- [Towards Relatable Explainable AI with the Perceptual Process](https://mlsanity.com/paper/2112.14005/) (2021)
- [Explainable Reinforcement Learning for Broad-XAI: A Conceptual Framework and Survey](https://mlsanity.com/paper/2108.09003/) (2021)
- [Counterfactual Plans under Distributional Ambiguity](https://mlsanity.com/paper/2201.12487/) (2022)
- [Contrastive Explanations of Plans Through Model Restrictions](https://mlsanity.com/paper/2103.15575/) (2021)
- [From Human Explanation to Model Interpretability: A Framework Based on Weight of Evidence](https://mlsanity.com/paper/2104.13299/) (2021)
- [A unified logical framework for explanations in classifier systems](https://mlsanity.com/paper/2105.14452/) (2021)
- [Diagnosing AI Explanation Methods with Folk Concepts of Behavior](https://mlsanity.com/paper/2201.11239/) (2022)
- [Directive Explanations for Actionable Explainability in Machine Learning Applications](https://mlsanity.com/paper/2102.02671/) (2021)
- [Contrastive Explanations That Anticipate Human Misconceptions Can Improve Human Decision-Making Skills](https://mlsanity.com/paper/2410.04253/) (2024)
- [Natural Example-Based Explainability: a Survey](https://mlsanity.com/paper/2309.03234/) (2023)
- [Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbation](https://mlsanity.com/paper/2101.06930/) (2021)
- [A Framework for Inherently Interpretable Optimization Models](https://mlsanity.com/paper/2208.12570/) (2022)
- [The Utility of "Even if..." Semifactual Explanation to Optimise Positive Outcomes](https://mlsanity.com/paper/2310.18937/) (2023)
- [Alterfactual Explanations -- The Relevance of Irrelevance for Explaining AI Systems](https://mlsanity.com/paper/2207.09374/) (2022)
- [A general-purpose method for applying Explainable AI for Anomaly Detection](https://mlsanity.com/paper/2207.11564/) (2022)
- [Towards a Framework for Evaluating Explanations in Automated Fact Verification](https://mlsanity.com/paper/2403.20322/) (2024)
- [Contrastive Explanations for Argumentation-Based Conclusions](https://mlsanity.com/paper/2107.03265/) (2021)
- [Improving Model Understanding and Trust with Counterfactual Explanations of Model Confidence](https://mlsanity.com/paper/2206.02790/) (2022)
- [Explaining Model Confidence Using Counterfactuals](https://mlsanity.com/paper/2303.05729/) (2023)
- [Contrastive Explanations of Centralized Multi-agent Optimization Solutions](https://mlsanity.com/paper/2308.05984/) (2023)
- [Forms of Understanding for XAI-Explanations](https://mlsanity.com/paper/2311.08760/) (2023)

## 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.