The Who in XAI: How AI Background Shapes Perceptions of AI Explanations

Abstract

Explainability of AI systems is critical for users to take informed actions. Understanding who "opens" with the black-box of AI is just as important as opening it. We conduct a mixed-methods study of how two different groups—people with and without AI background—perceive different types of AI explanations. Quantitatively, we share user perceptions along five dimensions. Qualitatively, we describe how AI background influences interpretations, elucidating the differences through lenses of appropriation and cognitive heuristics. We find that (1) both groups showed unwarranted faith in numbers for different reasons, (2) each group found value in different explanations beyond their intended design and (3) each group had different requirements for humanlike explanations. Carrying critical implications on XAI as a field, our findings showcase how AI generated explanations can have negative consequences despite best intentions and how that could lead to harmful manipulation of trust. We propose design interventions to mitigate them.