The Who in XAI: How AI Background Shapes Perceptions of AI Explanations
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2021
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916147797950464 |
|---|---|
| author | Ehsan, Upol Passi, Samir Liao, Q. Vera Chan, Larry Lee, I-Hsiang Muller, Michael Riedl, Mark O. |
| author_facet | Ehsan, Upol Passi, Samir Liao, Q. Vera Chan, Larry Lee, I-Hsiang Muller, Michael Riedl, Mark O. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2107_13509 |
| institution | arXiv |
| publishDate | 2021 |
| record_format | arxiv |
| spellingShingle | The Who in XAI: How AI Background Shapes Perceptions of AI Explanations Ehsan, Upol Passi, Samir Liao, Q. Vera Chan, Larry Lee, I-Hsiang Muller, Michael Riedl, Mark O. Human-Computer Interaction Artificial Intelligence Computers and Society 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. |
| title | The Who in XAI: How AI Background Shapes Perceptions of AI Explanations |
| topic | Human-Computer Interaction Artificial Intelligence Computers and Society |
| url | https://arxiv.org/abs/2107.13509 |