Abstract Argumentation and the Rational Man
This work addresses a gap in symbolic AI by analyzing abstract argumentation through microeconomic theory, offering a novel evaluation criterion for non-monotonic reasoning systems.
The paper tackles the problem of evaluating abstract argumentation from an economic rationality perspective, deriving a reference independence principle and showing that most existing semantics violate it, with cyclic expansions identified as the root cause.
Abstract argumentation has emerged as a method for non-monotonic reasoning that has gained popularity in the symbolic artificial intelligence community. In the literature, the different approaches to abstract argumentation that were refined over the years are typically evaluated from a formal logics perspective; an analysis that is based on models of economically rational decision-making does not exist. In this paper, we work towards addressing this issue by analyzing abstract argumentation from the perspective of the rational man paradigm in microeconomic theory. To assess under which conditions abstract argumentation-based decision-making can be considered economically rational, we derive reference independence as a non-monotonic inference property from a formal model of economic rationality and create a new argumentation principle that ensures compliance with this property. We then compare the reference independence principle with other reasoning principles, in particular with cautious monotony and rational monotony. We show that the argumentation semantics as proposed in Dung's seminal paper, as well as other semantics we evaluate -- with the exception of naive semantics and the SCC-recursive CF2 semantics -- violate the reference independence principle. Consequently, we investigate how structural properties of argumentation frameworks impact the reference independence principle, and identify cyclic expansions (both even and odd cycles) as the root of the problem. Finally, we put reference independence into the context of preference-based argumentation and show that for this argumentation variant, which explicitly models preferences, reference independence cannot be ensured in a straight-forward manner.