The Need for Standardized Explainability
It tackles the problem of inconsistent explainability methods for industry-grade AI, but it is incremental as it focuses on definitions and taxonomy without new empirical results.
The paper addresses the lack of standardization in explainable AI (XAI) by providing novel definitions for explainability and interpretability and proposing a tentative taxonomy of methods to facilitate future research.
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.