Explainable AI (XAI) has established itself as an important component of AI-driven interactive systems. With Augmented Reality (AR) becoming more integrated in daily lives, the role of XAI also becomes essential in AR because end-users will frequently interact with intelligent services. However, it is unclear how to design effective XAI experiences for AR. We propose XAIR, a design framework that addresses "when", "what", and "how" to provide explanations of AI output in AR. The framework was based on a multi-disciplinary literature review of XAI and HCI research, a large-scale survey probing 500+ end-users' preferences for AR-based explanations, and three workshops with 12 experts collecting their insights about XAI design in AR. XAIR's utility and effectiveness was verified via a study with 10 designers and another study with 12 end-users. XAIR can provide guidelines for designers, inspiring them to identify new design opportunities and achieve effective XAI designs in AR.
翻译：可解释人工智能(XAI)已经成为人工智能驱动交互系统的重要组成部分。随着增强现实(AR)越来越多地融入生活，XAI 在 AR 中的作用也变得至关重要，因为最终用户将频繁地与智能服务进行交互。然而，如何为 AR 设计有效的 XAI 经验尚不清楚。我们提出的 XAIR 是一个设计框架，它解决了在 AR 中何时、何种情况和如何提供人工智能输出的解释的问题。该框架基于对人机交互(HCI)研究和XAI 研究的多学科文献综述，对 500 多名最终用户进行了大规模调查，了解了他们对基于 AR 的解释的偏好，并且在三个专家讲习班中收集了他们关于在 AR 中设计 XAI 的见解。通过与 10 位设计师的研究以及另外一项 12 位最终用户的研究验证了 XAIR 的效用和有效性。XAIR 可以为设计师提供指南，激发他们识别新的设计机会并在 AR 中实现有效的 XAI 设计。
相关内容
微信扫码咨询专知VIP会员