What do we want from Explainable Artificial Intelligence (XAI)? – A stakeholder perspective on XAI and a conceptual model guiding interdisciplinary XAI research

Artificial Intelligence 296 (C):103473 (2021)
  Copy   BIBTEX


Previous research in Explainable Artificial Intelligence (XAI) suggests that a main aim of explainability approaches is to satisfy specific interests, goals, expectations, needs, and demands regarding artificial systems (we call these “stakeholders' desiderata”) in a variety of contexts. However, the literature on XAI is vast, spreads out across multiple largely disconnected disciplines, and it often remains unclear how explainability approaches are supposed to achieve the goal of satisfying stakeholders' desiderata. This paper discusses the main classes of stakeholders calling for explainability of artificial systems and reviews their desiderata. We provide a model that explicitly spells out the main concepts and relations necessary to consider and investigate when evaluating, adjusting, choosing, and developing explainability approaches that aim to satisfy stakeholders' desiderata. This model can serve researchers from the variety of different disciplines involved in XAI as a common ground. It emphasizes where there is interdisciplinary potential in the evaluation and the development of explainability approaches.

Similar books and articles

Connectionism and Artificial Intelligence: History and Philosophical Interpretation.Kenneth Aizawa - 1992 - Journal for Experimental and Theoretical Artificial Intelligence 4:1992.
Diversity of Rule-Based Approaches: Classic Systems and Recent Applications.Grzegorz J. Nalepa - 2016 - Avant: Trends in Interdisciplinary Studies 7 (2):104-116.
The Philosophy of Artificial Intelligence.Margaret A. Boden (ed.) - 1990 - Oxford, England: Oxford University Press.


Added to PP

227 (#53,100)

6 months
60 (#14,590)

Historical graph of downloads
How can I increase my downloads?

Author Profiles

Kevin Baum
Universität des Saarlandes
Eva Schmidt
TU Dortmund