arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2102.02437cs.HC
收藏

EUCA:以最终用户为中心的可解释AI框架

EUCA: the End-User-Centered Explainable AI Framework

Weina Jin, Jianyu Fan, Diane Gromala, Philippe Pasquier, Ghassan Hamarneh

摘要:

向最终用户解释决策的能力是部署AI作为关键决策支持的必要条件。然而,让人工智能向非技术终端用户解释是一个相对被忽视和具有挑战性的问题。为了弥补这一差距,我们首先确定了12个最终用户友好的解释形式,不需要技术知识来理解,包括基于特征,示例和规则的解释。然后,我们在四个人工智能辅助的关键决策任务中将解释性表格实例化为原型卡,并进行用户研究,与32名外行参与者共同设计低保真度原型。研究结果证实了使用解释形式作为解释的基石的相关性,并确定了它们的特性-优点,缺点,适用的解释目标和设计含义。解释性表单、它们的属性和原型支持(包括建议的原型设计过程、设计模板和范例以及实现解释性表单的相关算法)构成了以最终用户为中心的可解释AI框架EUCA,可在http://weinajin.github.io/end-user-xai上获得。它是一个实用的原型工具包,供HCI/AI从业者和研究人员了解用户需求并构建以最终用户为中心的可解释AI。

英文摘要:

The ability to explain decisions to end-users is a necessity to deploy AI as critical decision support. Yet making AI explainable to non-technical end-users is a relatively ignored and challenging problem. To bridge the gap, we first identify twelve end-user-friendly explanatory forms that do not require technical knowledge to comprehend, including feature-, example-, and rule-based explanations. We then instantiate the explanatory forms as prototyping cards in four AI-assisted critical decision-making tasks, and conduct a user study to co-design low-fidelity prototypes with 32 layperson participants. The results confirm the relevance of using explanatory forms as building blocks of explanations, and identify their proprieties - pros, cons, applicable explanation goals, and design implications. The explanatory forms, their proprieties, and prototyping supports (including a suggested prototyping process, design templates and exemplars, and associated algorithms to actualize explanatory forms) constitute the End-User-Centered explainable AI framework EUCA, and is available at http://weinajin.github.io/end-user-xai . It serves as a practical prototyping toolkit for HCI/AI practitioners and researchers to understand user requirements and build end-user-centered explainable AI.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑