Explainability Auditing for Intelligent Systems: A Rationale for Multi-Disciplinary Perspectives

TL;DR

This paper advocates for multi-disciplinary explainability auditing in AI systems to ensure quality, meet standards, and facilitate certification, emphasizing perspectives from technical, psychological, ethical, and legal domains.

Contribution

It introduces a multi-disciplinary framework for explainability auditing in AI, highlighting its role in quality assurance and certification processes.

Findings

Explainability auditing can verify system transparency and trustworthiness.

A multi-disciplinary approach enhances the effectiveness of explainability assessments.

Different perspectives provide comprehensive benefits for auditing processes.

Abstract

National and international guidelines for trustworthy artificial intelligence (AI) consider explainability to be a central facet of trustworthy systems. This paper outlines a multi-disciplinary rationale for explainability auditing. Specifically, we propose that explainability auditing can ensure the quality of explainability of systems in applied contexts and can be the basis for certification as a means to communicate whether systems meet certain explainability standards and requirements. Moreover, we emphasize that explainability auditing needs to take a multi-disciplinary perspective, and we provide an overview of four perspectives (technical, psychological, ethical, legal) and their respective benefits with respect to explainability auditing.