2nd International Workshop on Argumentation for eXplainable AI (ArgXAI)
Co-located with ICLP 2023 (London, UK)
In recent years, research on intelligent systems that can explain their inferences and decisions to (human and machine) users has emerged as an important subfield of Artificial Intelligence (AI). In this context, the interest in symbolic and hybrid approaches to AI and their ability to facilitate explainable and trustworthy reasoning and decision-making -- often in combination with machine learning algorithms -- is increasing. Computational argumentation is considered a particularly promising paradigm for facilitating explainable AI (XAI), and one that has deep roots in logic programming (LP). This trend is reflected by the fact that many researchers who study argumentation have started to:

apply argumentation as a method of explainable reasoning;
combine argumentation with other subfields of AI, such as knowledge representation and reasoning (KR), particularly forms of LP, as well as machine learning (ML), to facilitate the latter's explainability;
study explainability properties of argumentation and other defeasible reasoning approaches.

Given the substantial interest in these different facets of XAI in the context of argumentation and LP, this workshop aims at providing a forum for focused discussions of the recent developments on the topic. The workshop will feature works and discussions on diverse perspectives of argumentative and LP explainability. Specifically, we will cover the formal foundations of explaining argumentative inferences and argumentative properties of explanations, as well as applications of argumentation to facilitate explainability, with an extended focus on LP-based inference and explanations. The event would appeal to a wide range of researchers including: the growing sector of the core argumentation community that works on explainable argumentation; those working on explainability in the context of other approaches to defeasible reasoning, particularly LP; as well as to applied researchers who intend to use computational argumentation or LP for explainability purposes.

Topics
The aim of this workshop is to bring together researchers from the fields of computational argumentation, LP and eXplainable Artificial Intelligence (XAI). We specifically seek contributions that present formal work on argumentative explainability, as well as argumentative approaches that explain the behaviour of intelligent systems (argumentation for XAI). Topics include, but are not limited to:

* Symbolic Explainability
* Formal definitions of explanations
* Defeasible reasoning- and LP-based inference and explanations
* Computational properties of explanations
* Neuro-symbolic explainable argumentation
* Explanation as a form of argumentation or defeasible reasoning
* Human intelligibility of formal argumentation
* Interpretability of LP-based explanations
* Dialectical, dialogical and conversational explanations
* AI methods to support argumentative explainability
* Analogous topics for other defeasible reasoning approaches
* Argumentation for XAI
* Applications of argumentation for explainability in the fields of AI (e.g. machine learning, machine reasoning, multi-agent systems, natural language processing) and overlapping fields of research (e.g. optimisation, human-computer interaction, philosophy and social sciences)
* User-acceptance and evaluation of argumentation-based explanations
* Software systems that provide argumentation-based explanations
* Applications of other defeasible reasoning approaches to XAI

Programme
The programme will feature paper presentations followed by general discussions, one or several invited talk(s), and an open or panel discussion.