Eye into AI: Evaluating the Interpretability of Explainable AI Techniques through a Game with a Purpose
Proceedings of the ACM on Human-Computer Interaction · 2023-09-28 · 7 (CSCW2) · 1-22
DOI: 10.1145/3610064 ↗At a glance
Journal article in Proceedings of the ACM on Human-Computer Interaction, published online on 2023-10-04. Written by Katelyn Morrison and 3 co-authors. Cited 11 times so far (Crossref); 64 references. The full text is freely available (open access, CC BY-NC-ND 4.0). Funded by: National Heart, Lung, and Blood Institute.
Abstract (original language)
Recent developments in explainable AI (XAI) aim to improve the transparency of black-box models. However, empirically evaluating the interpretability of these XAI techniques is still an open challenge. The most common evaluation method is algorithmic performance, but such an approach may not accurately represent how interpretable these techniques are to people. A less common but growing evaluation strategy is to leverage crowd-workers to provide feedback on multiple XAI techniques to compare them. However, these tasks often feel like work and may limit participation. We propose a novel, playful, human-centered method for evaluating XAI techniques: a Game With a Purpose (GWAP), Eye into AI, that allows researchers to collect human evaluations of XAI at scale. We provide an empirical study demonstrating how our GWAP supports evaluating and comparing the agreement between three popular XAI techniques (LIME, Grad-CAM, and Feature Visualization) and humans, as well as evaluating and comparing the interpretability of those three XAI techniques applied to a deep learning model for image classification. The data collected from Eye into AI offers convincing evidence that GWAPs can be used to evaluate and compare XAI techniques. Eye into AI is available to the public: https://dig.cmu.edu/eyeintoai/.
Funding
- National Heart, Lung, and Blood Institute
Cite
APA
Morrison, K., Jain, M., Hammer, J., & Perer, A. (2023). Eye into AI: Evaluating the Interpretability of Explainable AI Techniques through a Game with a Purpose. Proceedings of the ACM on Human-Computer Interaction, 7(CSCW2), 1-22. https://doi.org/10.1145/3610064
Vancouver
Morrison K, Jain M, Hammer J, Perer A. Eye into AI: Evaluating the Interpretability of Explainable AI Techniques through a Game with a Purpose. Proceedings of the ACM on Human-Computer Interaction. 2023;7(CSCW2):1-22. doi:10.1145/3610064
BibTeX
@article{Morrison2023,
author = {Morrison, Katelyn and Jain, Mayank and Hammer, Jessica and Perer, Adam},
title = {Eye into AI: Evaluating the Interpretability of Explainable AI Techniques through a Game with a Purpose},
journal = {Proceedings of the ACM on Human-Computer Interaction},
year = {2023},
volume = {7},
number = {CSCW2},
pages = {1--22},
doi = {10.1145/3610064}
}
EUVIMED