🤖 AI Summary
This work addresses the problem of automatically learning acceptability semantics in formal argumentation. We propose the first unified, interpretable learning framework based on Inductive Logic Programming (ILP), supporting diverse argumentation models—including Abstract Argumentation Frameworks (AFs), AFs with Recursive Attacks (AFRA), and Symmetric Extended AFs (SETAFs). Unlike existing black-box approaches, our method introduces ILP to argumentation semantics learning for the first time, explicitly encoding acceptance criteria as human-readable logical rules—thereby ensuring both high interpretability and strong generalization. Empirical evaluation demonstrates that our framework significantly outperforms state-of-the-art argumentation solvers in both accuracy and cross-framework generalization. It thus establishes a novel paradigm for argument identification in trustworthy human–AI dialogue systems.
📝 Abstract
Argumentation is a very active research field of Artificial Intelligence concerned with the representation and evaluation of arguments used in dialogues between humans and/or artificial agents. Acceptability semantics of formal argumentation systems define the criteria for the acceptance or rejection of arguments. Several software systems, known as argumentation solvers, have been developed to compute the accepted/rejected arguments using such criteria. These include systems that learn to identify the accepted arguments using non-interpretable methods. In this paper we present a novel framework, which uses an Inductive Logic Programming approach to learn the acceptability semantics for several abstract and structured argumentation frameworks in an interpretable way. Through an empirical evaluation we show that our framework outperforms existing argumentation solvers, thus opening up new future research directions in the area of formal argumentation and human-machine dialogues.
