What Do We Want From Explainable Artificial Intelligence (XAI)? -- A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research

TL;DR

This paper reviews stakeholder needs in XAI, identifies key desiderata, and proposes a conceptual model to guide interdisciplinary research and evaluation of explainability approaches.

Contribution

It introduces a comprehensive model outlining stakeholder desiderata and their relations, fostering interdisciplinary collaboration in XAI research and development.

Findings

Stakeholders have diverse desiderata for explainability.

A conceptual model clarifies concepts and relations in XAI evaluation.

The model promotes interdisciplinary research and development in XAI.

Abstract

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.