EUCA: the End-User-Centered Explainable AI Framework
This work provides a practical prototyping toolkit for HCI/AI practitioners and researchers to understand user requirements and build end-user-centered explainable AI, addressing a critical need for deploying AI in decision support.
This paper addresses the challenge of making AI explanations accessible to non-technical end-users by identifying twelve end-user-friendly explanatory forms. Through a user study with 32 layperson participants, the research confirms the relevance of these forms and identifies their properties, leading to the development of the EUCA framework.
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.