XAIR: A Framework of Explainable AI in Augmented Reality
Abstract
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.
BibTeX
@inproceedings{10.1145/3544548.3581500,
author = {Xu, Xuhai and Yu, Anna and Jonker, Tanya R. and Todi, Kashyap and Lu, Feiyu and Qian, Xun and Evangelista Belo, Jo\~{a}o Marcelo and Wang, Tianyi and Li, Michelle and Mun, Aran and Wu, Te-Yen and Shen, Junxiao and Zhang, Ting and Kokhlikyan, Narine and Wang, Fulton and Sorenson, Paul and Kim, Sophie and Benko, Hrvoje},
title = {XAIR: A Framework of Explainable AI in Augmented Reality},
year = {2023},
isbn = {9781450394215},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3544548.3581500},
doi = {10.1145/3544548.3581500},
abstract = {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.},
booktitle = {Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems},
articleno = {202},
numpages = {30},
keywords = {Augmented Reality, Design Framework, Explainable AI},
location = {Hamburg, Germany},
series = {CHI '23}
}