期刊
ARTIFICIAL INTELLIGENCE
卷 296, 期 -, 页码 -出版社
ELSEVIER
DOI: 10.1016/j.artint.2021.103473
关键词
Explainable Artificial Intelligence; Explainability; Interpretability; Explanations; Understanding; Interdisciplinary Research; Human-Computer Interaction
资金
- Volkswagen Foundation [AZ 95143, AZ 98509, AZ 98510, AZ 98511, AZ 98512, AZ 98513, AZ 98514]
- DFG [389792660, TRR248]
- ERC [695614]
This paper discusses the classification of stakeholders and their desires in Explainable Artificial Intelligence (XAI), and proposes a model to explicitly explain the main concepts and relationships needed to fulfill stakeholders' desires.
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. (C) 2021 Elsevier B.V. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据