The Case for "Thick Evaluations" of Cultural Representation in AI
This addresses the problem of inadequate cultural representation in AI for marginalized communities, offering a novel evaluation approach that is incremental in refining existing methods.
The authors argue that current evaluations of cultural representation in AI image models are reductive and propose 'thick evaluations' as a more granular, situated framework based on community workshops in South Asia to better align measurements with local experiences.
Generative AI image models have been increasingly evaluated for their (in)ability to represent non-Western cultures. We argue that these evaluations operate through reductive ideals of representation, abstracted from how people define their own representation and neglecting the inherently interpretive and contextual nature of cultural representation. In contrast to these 'thin' evaluations, we introduce the idea of 'thick evaluations': a more granular, situated, and discursive measurement framework for evaluating representations of social worlds in AI images, steeped in communities' own understandings of representation. We develop this evaluation framework through workshops in South Asia, by studying the 'thick' ways in which people interpret and assign meaning to images of their own cultures. We introduce practices for thicker evaluations of representation that expand the understanding of representation underpinning AI evaluations and by co-constructing metrics with communities, bringing measurement in line with the experiences of communities on the ground.