# An ASP-Based Approach to Counterfactual Explanations for Classification

arXiv: https://arxiv.org/abs/2004.13237 · HTML: https://mlsanity.com/paper/2004.13237/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Apr 2020.

## Built on by (most cited first, 10 of 10)

- [If Only We Had Better Counterfactual Explanations: Five Key Deficits to Rectify in the Evaluation of Counterfactual XAI Techniques](https://mlsanity.com/paper/2103.01035/) (2021)
- [Answer-Set Programs for Reasoning about Counterfactual Interventions and Responsibility Scores for Classification](https://mlsanity.com/paper/2107.10159/) (2021)
- [DiConStruct: Causal Concept-based Explanations through Black-Box Distillation](https://mlsanity.com/paper/2401.08534/) (2024)
- [Explainable Goal Recognition: A Framework Based on Weight of Evidence](https://mlsanity.com/paper/2303.05622/) (2023)
- [Score-Based Explanations in Data Management and Machine Learning: An Answer-Set Programming Approach to Counterfactual Analysis](https://mlsanity.com/paper/2106.10562/) (2021)
- [Learning Actionable Counterfactual Explanations in Large State Spaces](https://mlsanity.com/paper/2404.17034/) (2024)
- [Understanding Endogenous Data Drift in Adaptive Models with Recourse-Seeking Users](https://mlsanity.com/paper/2503.09658/) (2025)
- [Reasoning about Counterfactuals and Explanations: Problems, Results and Directions](https://mlsanity.com/paper/2108.11004/) (2021)
- [Generating Causally Compliant Counterfactual Explanations using ASP](https://mlsanity.com/paper/2502.09226/) (2025)
- [From Facts to Foils: Designing and Evaluating Counterfactual Explanations for Smart Environments](https://mlsanity.com/paper/2510.03078/) (2025)

## Abstract (arXiv)

We propose answer-set programs that specify and compute counterfactual interventions as a basis for causality-based explanations to decisions produced by classification models. They can be applied with black-box models and models that can be specified as logic programs, such as rule-based classifiers. The main focus in on the specification and computation of maximum responsibility causal explanations. The use of additional semantic knowledge is investigated.