TY - GEN
T1 - Towards Culturally Aware AI
T2 - 42nd Computer Graphics International Conference, CGI 2025
AU - Elsharif, Wala
AU - Alzubaidi, Mahmood
AU - She, James
AU - Agus, Marco
N1 - Publisher Copyright:
© The Author(s), under exclusive license to Springer Nature Switzerland AG 2026.
PY - 2026/7/2
Y1 - 2026/7/2
N2 - Despite advances in text-to-image models, issues like cultural bias and inaccuracy persist, underscoring the need for reliable quantitative metrics to evaluate cultural representation. This work introduces CRIX, a prompt-guided, context-aware Cultural Relevance Index that leverages visual language models (VLMs) and visual question answering (VQA) to assess both the content and context of AI-generated images. Applied to Arabic and South Asian cultures, CRIX achieves lower mean squared errors (0.0022 and 0.0053, respectively) than baseline metrics, indicating stronger alignment with human evaluations. We also propose the Cultural Similarity Score (CSS) to quantify how similarly two images reflect a target culture.
AB - Despite advances in text-to-image models, issues like cultural bias and inaccuracy persist, underscoring the need for reliable quantitative metrics to evaluate cultural representation. This work introduces CRIX, a prompt-guided, context-aware Cultural Relevance Index that leverages visual language models (VLMs) and visual question answering (VQA) to assess both the content and context of AI-generated images. Applied to Arabic and South Asian cultures, CRIX achieves lower mean squared errors (0.0022 and 0.0053, respectively) than baseline metrics, indicating stronger alignment with human evaluations. We also propose the Cultural Similarity Score (CSS) to quantify how similarly two images reflect a target culture.
KW - AI-Generated Content
KW - Evaluation Methods
KW - Generative Models
UR - https://www.scopus.com/pages/publications/105045813649
U2 - 10.1007/978-3-032-22267-1_26
DO - 10.1007/978-3-032-22267-1_26
M3 - Conference contribution
AN - SCOPUS:105045813649
SN - 9783032222664
VL - 16509
T3 - Lecture Notes In Computer Science
SP - 331
EP - 340
BT - Advances In Computer Graphics, Cgi 2025, Pt Iii
A2 - Li, P
A2 - Ma, L
A2 - Wan, L
A2 - Sheng, B
A2 - Kim, J
A2 - Thalmann, D
A2 - Magnenat-Thalmann, N
PB - Springer Science and Business Media Deutschland GmbH
Y2 - 14 July 2025 through 18 July 2025
ER -