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

Titelangaben

Langer, Markus ; Baum, Kevin ; Hartmann, Kathrin ; Hessel, Stefan ; Speith, Timo ; Wahl, Jonas:
Explainability Auditing for Intelligent Systems : A Rationale for Multi-Disciplinary Perspectives.
In: Yue, Tao ; Mirakhorli, Mehdi (Hrsg.): 2021 IEEE 29th International Requirements Engineering Conference Workshops (REW). - Piscataway, NJ, USA : IEEE , 2021 . - S. 164-168
ISBN 978-1-6654-1898-0
DOI: https://doi.org/10.1109/REW53955.2021.00030

Angaben zu Projekten

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.