The Who in XAI: How AI Background Shapes Perceptions of AI Explanations
This research addresses the problem of AI explainability for users, highlighting negative consequences and proposing design interventions, but it is incremental as it builds on existing XAI studies.
The study investigated how people with and without AI background perceive AI explanations, finding that both groups showed unwarranted faith in numbers for different reasons and valued different explanations beyond their intended design, which can lead to harmful manipulation of trust.
Explainability of AI systems is critical for users to take informed actions. Understanding "who" opens 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 can influence 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 and (2) each group found value in different explanations beyond their intended design. Carrying critical implications for the field of XAI, 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.