article · Journal of Artificial Intelligence Research
This research investigates whether explainable artificial intelligence (XAI) studies account for cultural differences in human explanatory needs. It highlights existing psychological research demonstrating significant variations in how people from Western, individualist countries and non-Western, collectivist countries provide and understand explanations. The analysis argues that current XAI research often overlooks these cultural nuances, implicitly assuming that Western explanatory needs are universally shared. A systematic review of over 200 XAI user studies revealed that most sampled only Western populations yet drew broad conclusions about human-XAI interactions. Furthermore, an examination of over 30 XAI literature reviews showed that cultural differences were rarely mentioned. This combined evidence points to a cultural bias towards Western populations in XAI research, identifying a critical knowledge gap concerning how diverse users interact with XAI systems.
Understanding cultural differences in how people interpret AI explanations is crucial for developing fair and effective AI systems. If XAI is biased towards one cultural perspective, it may not be trusted or understood by a global user base, limiting its usefulness and adoption across diverse communities.
The abstract identifies a significant research gap concerning cultural bias in XAI systems. While it does not indicate an immediate application pathway, addressing this bias through future research could lead to the development of more culturally sensitive and universally applicable XAI tools, benefiting organisations and users in diverse global markets.
AI-generated from the published abstract. Always read the original work before citing.
For synergistic interactions between humans and artificial intelligence (AI) systems, AI outputs often need to be explainable to people. Explainable AI (XAI) systems are commonly tested in human user studies. However, whether XAI researchers consider potential cultural differences in human explanatory needs remains unexplored. We highlight psychological research that found significant differences in human explanations between many people from Western, commonly individualist countries and people from non-Western, often collectivist countries. We argue that XAI research currently overlooks these variations and that many popular XAI designs implicitly and problematically assume that Western explanatory needs are shared cross-culturally. Additionally, we systematically reviewed over 200 XAI user studies and found that most studies did not consider relevant cultural variations, sampled only Western populations, but drew conclusions about human-XAI interactions more generally. We also analyzed over 30 literature reviews of XAI studies. Most reviews did not mention cultural differences in explanatory needs or flag overly broad cross-cultural extrapolations of XAI user study results. Combined, our analyses provide evidence of a cultural bias toward Western populations in XAI research, highlighting an important knowledge gap regarding how culturally diverse users may respond to widely used XAI systems that future work can and should address.
This page summarises published work. The authoritative version sits with the publisher.
DOI: 10.1613/jair.1.14888
Is something wrong with this record? Report it or request removal.
Discussion
Have you built on this work, tried to replicate it, or seen it applied in practice? Share what you know. Verified researchers and MARATTO™ domain experts can open a discussion, and any member can reply. Contributions are reviewed before they appear.
No discussion yet. Open the first thread.
New to MARATTO™? Create a free account.
