Gagan Bansal, Tongshuang Wu, Joyce Zhou, Raymond Fok, Besmira Nushi, Ece Kamar, Marco Tulio Ribeiro, & Daniel S. Weld (2021)
Proceedings of the SIGCHI Conference on Human Factors in Computing Systems (CHI '21), 1-16.
DOI: https://doi.org/10.1145/3411764.3445717
Abstract. Empirical study finding that AI explanations often fail to produce complementary human-AI team performance — instead they drive over-reliance. A sobering counterweight to the assumption that "explainable AI" automatically yields better human-AI decisions.
Tags: ai-usability trust xai