Skip to main content Skip to main navigation

Publikation

Multilingual Text-to-Image Generation Magnifies Gender Stereotypes

Felix Friedrich; Katharina Hämmerl; Patrick Schramowski; Manuel Brack; Jindrich Libovický; Alexander Fraser; Kristian Kersting
In: Wanxiang Che; Joyce Nabende; Ekaterina Shutova; Mohammad Taher Pilehvar (Hrsg.). Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), ACL 2025, Vienna, Austria, July 27 - August 1, 2025. Annual Meeting of the Association for Computational Linguistics (ACL), Pages 19656-19679, Association for Computational Linguistics, 2025.

Zusammenfassung

Text-to-image (T2I) generation models have achieved great results in image quality, flexibil- ity, and text alignment, leading to widespread use. Through improvements in multilingual abilities, a larger community can access this technology. Yet, we show that multilingual models suffer from substantial gender bias. Fur- thermore, the expectation that results should be similar across languages does not hold. We introduce MAGBIG, a controlled benchmark de- signed to study gender bias in multilingual T2I models, and use it to assess the impact of multi- lingualism on gender bias. To this end, we construct a set of multilingual prompts that offers a carefully controlled setting account- ing for the complex grammatical differences influencing gender across languages. Our re- sults show strong gender biases and notable language-specific differences across models. While we explore prompt engineering strate- gies to mitigate these biases, we find them largely ineffective and sometimes even detri- mental to text-to-image alignment. Our analy- sis highlights the need for research on diverse language representations and greater control over bias in T2I models.1

Weitere Links