Explainable AI: A Review of the Empirical Literature

20 Pages Posted: 18 Jan 2023

See all articles by Serhiy Kandul

Serhiy Kandul

University of Zurich

Vincent Micheli

University of Geneva

Juliane Beck

University of St. Gallen

Markus Kneer

University of Zurich - Institute of Philosophy

Thomas Burri

University of St. Gallen

François Fleuret

University of Geneva

Markus Christen

University of Zurich

Date Written: January 16, 2023

Abstract

AI deep learning models have become more capable, but also more complex and less explainable. To address this development, new research on so-called explainable AI (XAI) has proliferated. This paper surveys the empirical literature on XAI based on human-subject experiments. It classifies extant work across different technical and experimental dimensions. Our findings suggest that explainable AI improves self-reported understanding and trust in AI. However, this rarely translates into improved performance of humans in incentivized tasks with AI support. We list several implications of these findings concerning the use of explainable AI in human-computer interaction.

Keywords: Explainable AI, human perception, experiments, human-computer interaction

Suggested Citation

Kandul, Serhiy and Micheli, Vincent and Beck, Juliane and Kneer, Markus and Burri, Thomas and Fleuret, François and Christen, Markus, Explainable AI: A Review of the Empirical Literature (January 16, 2023). Available at SSRN: https://ssrn.com/abstract=4325219 or http://dx.doi.org/10.2139/ssrn.4325219

Serhiy Kandul

University of Zurich ( email )

Vincent Micheli

University of Geneva ( email )

Juliane Beck (Contact Author)

University of St. Gallen ( email )

Markus Kneer

University of Zurich - Institute of Philosophy ( email )

Thomas Burri

University of St. Gallen ( email )

Bodanstrasse 3
Saint Gallen, St. Gallen CH-9000
Switzerland

HOME PAGE: http://www.unisg.ch/en/universitaet/schools/law/ueber-ls/faculty/burri

François Fleuret

University of Geneva ( email )

Markus Christen

University of Zurich ( email )

Rämistrasse 71
Zürich, CH-8006
Switzerland

Do you have a job opening that you would like to promote on SSRN?

Paper statistics

Downloads
444
Abstract Views
1,137
Rank
125,147
PlumX Metrics