Interactive Explanations by Conflict Resolution via Argumentative Exchanges

TL;DR

This paper introduces a novel interactive explanation framework for AI models using conflict resolution through argumentative exchanges, enabling dynamic multi-agent interactions that improve understanding and address biases.

Contribution

It proposes Argumentative eXchanges (AXs) for multi-agent conflict resolution in XAI, integrating argumentation frameworks with agent behaviors for improved explanations.

Findings

AXs effectively resolve conflicts in simulated environments.

Counterfactual reasoning enhances explanation quality.

Strongest argument isn't always most persuasive.

Abstract

As the field of explainable AI (XAI) is maturing, calls for interactive explanations for (the outputs of) AI models are growing, but the state-of-the-art predominantly focuses on static explanations. In this paper, we focus instead on interactive explanations framed as conflict resolution between agents (i.e. AI models and/or humans) by leveraging on computational argumentation. Specifically, we define Argumentative eXchanges (AXs) for dynamically sharing, in multi-agent systems, information harboured in individual agents' quantitative bipolar argumentation frameworks towards resolving conflicts amongst the agents. We then deploy AXs in the XAI setting in which a machine and a human interact about the machine's predictions. We identify and assess several theoretical properties characterising AXs that are suitable for XAI. Finally, we instantiate AXs for XAI by defining various agent behaviours, e.g. capturing counterfactual patterns of reasoning in machines and highlighting the effects of cognitive biases in humans. We show experimentally (in a simulated environment) the comparative advantages of these behaviours in terms of conflict resolution, and show that the strongest argument may not always be the most effective.