A Survey of Explainable AI and Proposal for a Discipline of Explanation Engineering

TL;DR

This survey comprehensively reviews Explainable AI, categorizes existing methods, explores applications across key domains, and proposes a new discipline called Explanation Engineering for systematic explainability design.

Contribution

It provides a detailed taxonomy of XAI methods, analyzes their applications, and introduces the concept of Explanation Engineering as a systematic approach.

Findings

Taxonomy of XAI methods

Applications in finance, autonomous driving, healthcare, manufacturing

Proposal of Explanation Engineering discipline

Abstract

In this survey paper, we deep dive into the field of Explainable Artificial Intelligence (XAI). After introducing the scope of this paper, we start by discussing what an "explanation" really is. We then move on to discuss some of the existing approaches to XAI and build a taxonomy of the most popular methods. Next, we also look at a few applications of these and other XAI techniques in four primary domains: finance, autonomous driving, healthcare and manufacturing. We end by introducing a promising discipline, "Explanation Engineering," which includes a systematic approach for designing explainability into AI systems.