Tags:Explainable Artificial Intelligence, Formal Argumentation and Non-monotonic Reasoning
Abstract:
In this paper, we introduce a formal framework for the principle-based explanation of change of inference in abstract argumentation, in particular in the context of iterative inferences from a sequence of normal expansions, with a focus on admissible set-based semantics. The results allow us to provide, given an initial argumentation framework and an extension that has been inferred from it, principle-based explanations for the violation of monotony when inferring an extension from a normal expansion of the initial argumentation framework.
Explanations of Non-Monotonic Inference in Admissibility-Based Abstract Argumentation