EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Navigating Cultural Chasms: Exploring and Unlocking the Cultural POV of Text-To-Image Models

Mor Ventura, Eyal Ben-David, Anna Korhonen, Roi Reichart

Transactions of the Association for Computational Linguistics · 17.02.2025 · 13 · 142-166

DOI: 10.1162/tacl_a_00732 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Transactions of the Association for Computational Linguistics, online erschienen am 17.02.2025. Verfasst von Mor Ventura und 3 weiteren Autor:innen. Die Arbeit wurde bisher 9-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Text-To-Image (TTI) models, such as DALL-E and StableDiffusion, have demonstrated remarkable prompt-based image generation capabilities. Multilingual encoders may have a substantial impact on the cultural agency of these models, as language is a conduit of culture. In this study, we explore the cultural perception embedded in TTI models by characterizing culture across three tiers: cultural dimensions, cultural domains, and cultural concepts. Based on this ontology, we derive prompt templates to unlock the cultural knowledge in TTI models, and propose a comprehensive suite of evaluation techniques, including intrinsic evaluations using the CLIP space, extrinsic evaluations with a Visual-Question-Answer models and human assessments, to evaluate the cultural content of TTI-generated images. To bolster our research, we introduce the CulText2I dataset, based on six diverse TTI models and spanning ten languages. Our experiments provide insights regarding Do, What, Which, and How research questions about the nature of cultural encoding in TTI models, paving the way for cross-cultural applications of these models.1

Zitieren

APA

Ventura, M., Ben-David, E., Korhonen, A., & Reichart, R. (2025). Navigating Cultural Chasms: Exploring and Unlocking the Cultural POV of Text-To-Image Models. Transactions of the Association for Computational Linguistics, 13, 142-166. https://doi.org/10.1162/tacl_a_00732

Vancouver

Ventura M, Ben-David E, Korhonen A, Reichart R. Navigating Cultural Chasms: Exploring and Unlocking the Cultural POV of Text-To-Image Models. Transactions of the Association for Computational Linguistics. 2025;13:142-166. doi:10.1162/tacl_a_00732

BibTeX
@article{Ventura2025,
  author = {Ventura, Mor and Ben-David, Eyal and Korhonen, Anna and Reichart, Roi},
  title = {Navigating Cultural Chasms: Exploring and Unlocking the Cultural POV of Text-To-Image Models},
  journal = {Transactions of the Association for Computational Linguistics},
  year = {2025},
  volume = {13},
  pages = {142--166},
  doi = {10.1162/tacl_a_00732}
}
Kostenlos starten →