Reconciling Explanations in Multi-Model Systems through Probabilistic Argumentation

TL;DR

This paper proposes a probabilistic argumentation framework to reconcile conflicting explanations in multi-model AI systems, enhancing coherence and alignment with human reasoning in high-stakes domains.

Contribution

It introduces a novel probabilistic argumentation approach for explanation reconciliation in multi-model systems, addressing conflicts and incorporating user perspectives.

Findings

Framework effectively reconciles conflicting explanations.

Incorporates user perspectives like optimism and fairness.

Optimizes explanation search space with relative independence assumption.

Abstract

Explainable Artificial Intelligence (XAI) has become critical in enhancing the transparency and trustworthiness of AI systems, especially as these systems are increasingly deployed in high-stakes domains such as healthcare and finance. Despite the progress made in developing explanation generation techniques for individual machine learning (ML) models, significant challenges remain in achieving coherent and comprehensive explanations in multi-model systems. This paper addresses these challenges by focusing on the explanation reconciliation problem (ERP) within multi-model systems. Traditional explanation generation technique often fall short in multi-model systems contexts, where explanations from different models can conflict and fail to form a cohesive narrative. Through the use of probabilistic argumentation and knowledge representation techniques, we propose a framework for generating holistic explanations that align with human cognitive processes. Our approach involves mapping uncertain explanation information to probabilistic arguments and introducing criteria for explanation reconciliation based on user perspectives such as optimism, pessimism, fairness. In addition, we introduce the relative independence assumption to optimise the search space for computational explanations.