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

TL;DR

This paper explores the formal foundations, complexity, and computational methods for counterfactual and semifactual explanations in abstract argumentation, addressing a gap in explainability techniques for argumentation systems.

Contribution

It introduces a formal analysis of counterfactual and semifactual reasoning in abstract argumentation and proposes a computational approach using ASP solvers.

Findings

Counterfactual and semifactual reasoning are computationally harder than classical argumentation problems.

Counterfactual and semifactual queries can be encoded in weak-constrained Argumentation Frameworks.

A computational strategy using ASP solvers is proposed for these reasoning problems.

Abstract

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.