Are explainable AI (XAI) evaluation strategies aligned? Comparing subjective, objective, and mathematical evaluation measures using saliency maps
It is found that each family of methods leads to different conclusions: participants reported no differences in trust or satisfaction, Grad-CAM improved user performance, while mathematical metrics favored Guided Backpropagation, and implications for XAI evaluation frameworks are discussed.
Felix Kares, Timo Speith, Hanwei Zhang et al.
· Computers in Human Behavior · 14 citations