Necessary and Sufficient Explanations in Abstract Argumentation
This addresses the need for interpretability in AI systems using argumentation, but it appears incremental as it builds on existing formal argumentation concepts.
The paper tackles the problem of explaining why arguments are accepted or not in formal argumentation by studying necessary and sufficient explanations under various semantics, resulting in a framework for deriving such explanations.
In this paper, we discuss necessary and sufficient explanations for formal argumentation - the question whether and why a certain argument can be accepted (or not) under various extension-based semantics. Given a framework with which explanations for argumentation-based conclusions can be derived, we study necessity and sufficiency: what (sets of) arguments are necessary or sufficient for the (non-)acceptance of an argument?