Computational argumentation studies fundamental methods for reasoning within Artificial Intelligence (AI). Two prominent subfields in computational argumentation are abstract argumentation and structured argumentation. Abstract argumentation focuses on the interactions between arguments, ignoring their internal structure, while structured approaches utilize a given knowledge base to construct the arguments. Thus, the latter approach incorporates the internal structure of arguments into the reasoning process. In this work we introduce a form of abstraction on the well established structured approach of Assumption-Based Argumentation (ABA). Our goal is to provide methods to simplify complicated scenarios, by applying clustering over defeasible parts. Abstraction, particularly clustering, has been explored in recent research on abstract argumentation and in the adjacent field of logic programming. In fact, while clustering has also been applied to ABA, our approach takes a different, or rather dual, direction. In contrast to prior work on over-approximation on ABA, we propose the dual approach of under-approximation. We provide semantics for reasoning over clustered frameworks in a sound manner relative to original semantics, ensuring that any set deemed acceptable in the clustered scenario corresponds to an acceptable set. We show properties of the under-approximating semantics and illustrate our approach using a conceptual example based on medical recommendations.

Approaches to computational argumentation provide foundational ways to reason argumentatively within Artificial Intelligence (AI). The underlying formal approaches can oftentimes be classified into structured argumentation and abstract argumentation. The former prescribe rigorous workflows, starting from knowledge bases to finding arguments in favour and against claims under scrutiny, and drawing conclusions. Abstract argumentation provides formal semantics operating on arguments whose internal structure is hidden and only relations are kept for reasoning, resulting in so-called argumentation frameworks (AFs). In this work, we apply a form of existential abstraction on the prominent structured approach of assumption-based argumentation (ABA), leading to an interactive way of simplifying argumentation scenarios by abstracting irrelevant details, towards supporting explainability. Existential abstraction was shown to be promising in many areas of AI, including a recent work on AFs. We lift this approach to the structured level---which is, as we show, both not direct from AFs and can benefit from utilization of the internal structure of arguments. Among our contributions, we introduce existential abstraction on ABA via clustering assumptions, develop semantics on clustered ABA frameworks for reasoning on such clusterings, show differences to the level of AFs, and provide a prototype interactive tool that obtains faithful clusterings that do not lead to any spurious reasoning.

Recently forms of abstraction have been proposed for both logic programs (LPs) under the answer set semantics (ASP) and for the related formalism of assumption-based argumentation (ABA), e.g., via clustering of atoms or assumptions, in order to simplify a given LP or ABA framework. In both approaches after clustering the original answer sets and assumption sets are over-approximated, with the aim of avoiding spuriousness. In contrast, in ASP a given LP is syntactically modified to achieve over-approximation, while on ABA the framework is minimally modified and the semantics is abstracted. In this work we follow the latter approach and provide a novel semantical abstraction for LPs and for ABA frameworks corresponding to LPs.