Reconciling Consistency-Based Diagnosis with Actual-Causality-Based Explanations

TL;DR

This paper explores the relationship between consistency-based diagnosis and actual causality within Explainable AI, aiming to bridge gaps and enhance understanding in explainability methods.

Contribution

It establishes connections between CBD and actual causality, highlighting potential benefits for XAI and explainable data management.

Findings

Links between CBD and causality are formalized.

Potential for improved explainability in AI systems.

Bridges between diagnosis and causality are identified.

Abstract

We establish, from the point of view of Explainable AI (XAI), connections between Consistency-Based Diagnosis (CBD), on one side, and Actual Causality and Causal Responsibility, on the other. CBD has received little attention from the XAI community. Connections between these two areas could have a fruitful impact on XAI and Explainable Data Management.