当前位置: X-MOL 学术arXiv.cs.SE › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Questioning the AI: Informing Design Practices for Explainable AI User Experiences
arXiv - CS - Software Engineering Pub Date : 2020-01-08 , DOI: arxiv-2001.02478
Q. Vera Liao, Daniel Gruen, Sarah Miller

A surge of interest in explainable AI (XAI) has led to a vast collection of algorithmic work on the topic. While many recognize the necessity to incorporate explainability features in AI systems, how to address real-world user needs for understanding AI remains an open question. By interviewing 20 UX and design practitioners working on various AI products, we seek to identify gaps between the current XAI algorithmic work and practices to create explainable AI products. To do so, we develop an algorithm-informed XAI question bank in which user needs for explainability are represented as prototypical questions users might ask about the AI, and use it as a study probe. Our work contributes insights into the design space of XAI, informs efforts to support design practices in this space, and identifies opportunities for future XAI work. We also provide an extended XAI question bank and discuss how it can be used for creating user-centered XAI.

中文翻译:

质疑人工智能:为可解释的人工智能用户体验提供设计实践信息

对可解释人工智能 (XAI) 的兴趣激增,导致了大量关于该主题的算法工作。虽然许多人认识到在 AI 系统中加入可解释性特征的必要性,但如何满足现实世界用户对理解 AI 的需求仍然是一个悬而未决的问题。通过采访 20 位从事各种 AI 产品的 UX 和设计从业者,我们试图找出当前 XAI 算法工作与实践之间的差距,以创建可解释的 AI 产品。为此,我们开发了一个基于算法的 XAI 问题库,其中用户对可解释性的需求表示为用户可能会询问的关于 AI 的原型问题,并将其用作研究探针。我们的工作有助于深入了解 XAI 的设计空间,为支持该空间中的设计实践的努力提供信息,并确定未来 XAI 工作的机会。
更新日期:2020-02-11
down
wechat
bug