{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T18:35:28Z","timestamp":1790879728279,"version":"4.1.0"},"reference-count":0,"publisher":"Association for the Advancement of Artificial Intelligence (AAAI)","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["AIES"],"abstract":"<jats:p>Generative AI image models have been increasingly evaluated\nfor their (in)ability to represent non-Western cultures. \nWe argue that these evaluations operate through reductive\nideals of representation, abstracted from how people define\ntheir own representation and neglecting the inherently\ninterpretive and contextual nature of cultural\nrepresentation. In contrast to these \"thin\" evaluations, we\nintroduce the idea of \"thick evaluations\": a more granular,\nsituated, and discursive measurement framework for\nevaluating representations of social worlds in AI images,\nsteeped in communities' own understandings of\nrepresentation. We develop this evaluation framework\nthrough workshops in South Asia, by studying the \"thick\"\nways in which people interpret and assign meaning to images\nof their own cultures. We introduce practices for thicker\nevaluations of representation that expand the understanding\nof representation underpinning AI evaluations and by\nco-constructing metrics with communities, bringing\nmeasurement in line with the experiences of communities on\nthe ground.<\/jats:p>","DOI":"10.1609\/aies.v8i3.36696","type":"journal-article","created":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T13:29:43Z","timestamp":1760534983000},"page":"2067-2080","source":"Crossref","is-referenced-by-count":4,"title":["The Case for \"Thick Evaluations\" of Cultural Representation in AI"],"prefix":"10.1609","volume":"8","author":[{"given":"Rida","family":"Qadri","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mark","family":"D\u00edaz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ding","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael","family":"Madaio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"9382","published-online":{"date-parts":[[2025,10,15]]},"container-title":["Proceedings of the AAAI\/ACM Conference on AI, Ethics, and Society"],"original-title":[],"link":[{"URL":"https:\/\/ojs.aaai.org\/index.php\/AIES\/article\/download\/36696\/38834","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/ojs.aaai.org\/index.php\/AIES\/article\/download\/36696\/38834","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T13:29:44Z","timestamp":1760534984000},"score":1,"resource":{"primary":{"URL":"https:\/\/ojs.aaai.org\/index.php\/AIES\/article\/view\/36696"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,15]]},"references-count":0,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2025,10,15]]}},"URL":"https:\/\/doi.org\/10.1609\/aies.v8i3.36696","relation":{},"ISSN":["3065-8365"],"issn-type":[{"value":"3065-8365","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,15]]}}}