Transparency and explainability of AI systems: From ethical guidelines to requirements
Transparency and explainability of AI systems: From ethical guidelines to requirements
复制标题
DOI：
10.1016/j.infsof.2023.107197
复制
发表时间：
2023-03-24
影响因子：
3.9
通讯作者：
Kujala, Sari
中科院分区：
文献类型：
--
作者：
Balasubramaniam, Nagadivya;Kauppinen, Marjo;Kujala, Sari
背景和动机：最近的研究强调透明度和可解释性是人工智能系统的重要质量要求。然而，仍然有相对较少的案例研究，描述了在practice.Objective界定这些质量要求的现状：本研究包括两个阶段。我们的研究的第一个目标是探索组织已经定义了透明和可解释的人工智能系统的发展，然后我们invest-tigated如何解释性要求可以在practice.Methods定义的道德准则：在第一阶段，我们分析了代表不同industries和公共部门的16个组织的道德准则。然后，我们进行了一项实证研究，与从业者一起评估第一阶段的结果。结果如下：对道德操守准则的分析表明，几乎所有组织都强调透明度的重要性，可解释性被视为透明度的一个组成部分。为了支持可解释性需求的定义，我们提出了一个可解释性组件模型，用于识别可解释性需求和一个用于表示可解释性需求的模板。本文还介绍了我们在实践中应用模型和模板的经验教训。贡献：对于研究人员来说，本文提供了组织认为AI系统的透明度，特别是可解释性重要的见解。对于从业者来说，这项研究提出了一种系统化和结构化的方法来定义人工智能系统的可解释性要求。此外，研究结果强调了一系列有助于定义AI系统可解释性的良好实践。
Context and Motivation: Recent studies have highlighted transparency and explainability as important quality requirements of AI systems. However, there are still relatively few case studies that describe the current state of defining these quality requirements in practice.Objective: This study consisted of two phases. The first goal of our study was to explore what ethical guidelines organizations have defined for the development of transparent and explainable AI systems and then we inves-tigated how explainability requirements can be defined in practice.Methods: In the first phase, we analyzed the ethical guidelines in 16 organizations representing different in-dustries and public sector. Then, we conducted an empirical study to evaluate the results of the first phase with practitioners. Results: The analysis of the ethical guidelines revealed that the importance of transparency is highlighted by almost all of the organizations and explainability is considered as an integral part of transparency. To support the definition of explainability requirements, we propose a model of explainability components for identifying explainability needs and a template for representing explainability requirements. The paper also describes the lessons we learned from applying the model and the template in practice.Contribution: For researchers, this paper provides insights into what organizations consider important in the transparency and, in particular, explainability of AI systems. For practitioners, this study suggests a systematic and structured way to define explainability requirements of AI systems. Furthermore, the results emphasize a set of good practices that help to define the explainability of AI systems.