I was reading a paper on the subject of explainable AI and interpretability, in particular the tendency of people (even experts) to excessively trusting explanations given by AI. In the intro the author describes riding in a self-driving car with a screen on the passenger side that depicts the car's vision and classification of the objects on the road, ostensibly to improve the level of trust in the car's decision-making. Later the author quotes a study in which experts in a field give good ratings to an AI's explanations for its decision-making, even when the explanations given are intentionally incorrect.
I cannot for the life of me remember which paper this is or what it covers in its main sections, and after searching through dozens of my saved papers as well as online search engines I cannot recover it. The paper also mentions a specific term for trusting machines/AI, which I also can't remember and would definitely help me find the paper if I could.
If anyone is familiar with this paper or the study it quotes, I would really appreciate a link.