The Need for Standardized Explainability

TL;DR

This paper emphasizes the importance of standardizing explainability in AI, reviews current methods, and proposes new definitions and a taxonomy to guide future research in the field.

Contribution

It introduces novel definitions for explainability and interpretability and offers a tentative taxonomy to standardize explainability methods in AI.

Findings

Current explainability methods lack standardization

Proposed new definitions for explainability and interpretability

Presented a taxonomy of explainability methods

Abstract

Explainable AI (XAI) is paramount in industry-grade AI; however existing methods fail to address this necessity, in part due to a lack of standardisation of explainability methods. The purpose of this paper is to offer a perspective on the current state of the area of explainability, and to provide novel definitions for Explainability and Interpretability to begin standardising this area of research. To do so, we provide an overview of the literature on explainability, and of the existing methods that are already implemented. Finally, we offer a tentative taxonomy of the different explainability methods, opening the door to future research.