Counterfactual and Semifactual Explanations in Abstract Argumentation: Formal Foundations, Complexity and Computation
This work addresses the problem of interpretability in formal argumentation for decision-making systems, representing an incremental advancement by applying existing explanation techniques to a new domain.
The paper tackles the lack of explainability in argumentation-based systems by exploring counterfactual and semifactual explanations in abstract argumentation frameworks, showing that these reasoning problems are computationally harder than classical argumentation problems and can be encoded and computed using ASP solvers.
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.