# Counterfactual and Semifactual Explanations in Abstract Argumentation: Formal Foundations, Complexity and Computation

arXiv: https://arxiv.org/abs/2405.04081 · HTML: https://mlsanity.com/paper/2405.04081/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 75 references that are in the map.
- First posted on arXiv 7 May 2024.

## Builds on (most cited first, 7 of 7)

- [Model Interpretability through the Lens of Computational Complexity](https://mlsanity.com/paper/2010.12265/) (2020)
- [Argumentative XAI: A Survey](https://mlsanity.com/paper/2105.11266/) (2021)
- [On Generating Plausible Counterfactual and Semi-Factual Explanations for Deep Learning](https://mlsanity.com/paper/2009.06399/) (2020)
- [Even if Explanations: Prior Work, Desiderata & Benchmarks for Semi-Factual XAI](https://mlsanity.com/paper/2301.11970/) (2023)
- [On the Semantics of Abstract Argumentation Frameworks: A Logic Programming Approach](https://mlsanity.com/paper/2008.02550/) (2020)
- [Interpretable Regional Descriptors: Hyperbox-Based Local Explanations](https://mlsanity.com/paper/2305.02780/) (2023)
- [A Comparative Study of Some Central Notions of ASPIC+ and DeLP](https://mlsanity.com/paper/1909.02810/) (2019)

## Built on by (most cited first, 2 of 2)

- [Choices and their Provenance: Explaining Stable Solutions of Abstract Argumentation Frameworks](https://mlsanity.com/paper/2506.01087/) (2025)
- [Beyond But-for Test: Counterfactual Explanation in Abstract Argumentation via Actual Causality (Extended Version)](https://mlsanity.com/paper/2606.31080/) (2026)

## Abstract (arXiv)

Explainable Artificial Intelligence and Formal Argumentation have received significant attention in recent years. Argumentation-based systems often lack explainability while supporting decision-making processes. Counterfactual and semifactual explanations are interpretability techniques that provide insights into the outcome of a model by generating alternative hypothetical instances. While there has been important work on counterfactual and semifactual explanations for Machine Learning models, less attention has been devoted to these kinds of problems in argumentation. In this paper, we explore counterfactual and semifactual reasoning in abstract Argumentation Framework. We investigate the computational complexity of counterfactual- and semifactual-based reasoning problems, showing that they are generally harder than classical argumentation problems such as credulous and skeptical acceptance. Finally, we show that counterfactual and semifactual queries can be encoded in weak-constrained Argumentation Framework, and provide a computational strategy through ASP solvers.