Dialectical Reconciliation via Structured Argumentative Dialogues

TL;DR

This paper introduces a structured argumentation framework for human-AI dialogue that improves understanding by addressing knowledge gaps through dialectical reconciliation, supported by formal semantics and experimental validation.

Contribution

It extends model reconciliation with a formal, dialogue-based approach for better human-AI communication, including theoretical guarantees and empirical evaluation.

Findings

Framework enhances human understanding of AI decisions.

Formal semantics ensure reliable dialogue interactions.

Experimental results show improved explainability in practice.

Abstract

We present a novel framework designed to extend model reconciliation approaches, commonly used in human-aware planning, for enhanced human-AI interaction. By adopting a structured argumentation-based dialogue paradigm, our framework enables dialectical reconciliation to address knowledge discrepancies between an explainer (AI agent) and an explainee (human user), where the goal is for the explainee to understand the explainer's decision. We formally describe the operational semantics of our proposed framework, providing theoretical guarantees. We then evaluate the framework's efficacy ``in the wild'' via computational and human-subject experiments. Our findings suggest that our framework offers a promising direction for fostering effective human-AI interactions in domains where explainability is important.