Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2508.03199 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911415546150912 |
|---|---|
| author | Saeed, Muhammed Raza, Shaina Vayani, Ashmal Abdul-Mageed, Muhammad Emami, Ali Shehata, Shady |
| author_facet | Saeed, Muhammed Raza, Shaina Vayani, Ashmal Abdul-Mageed, Muhammad Emami, Ali Shehata, Shady |
| contents | Research on bias in Text-to-Image (T2I) models has primarily focused on demographic representation and stereotypical attributes, overlooking a fundamental question: how does grammatical gender influence visual representation across languages? We introduce a cross-linguistic benchmark examining words where grammatical gender contradicts stereotypical gender associations (e.g., ``une sentinelle'' - grammatically feminine in French but referring to the stereotypically masculine concept ``guard''). Our dataset spans five gendered languages (French, Spanish, German, Italian, Russian) and two gender-neutral control languages (English, Chinese), comprising 800 unique prompts that generated 28,800 images across three state-of-the-art T2I models. Our analysis reveals that grammatical gender dramatically influences image generation: masculine grammatical markers increase male representation to 73% on average (compared to 22% with gender-neutral English), while feminine grammatical markers increase female representation to 38% (compared to 28% in English). These effects vary systematically by language resource availability and model architecture, with high-resource languages showing stronger effects. Our findings establish that language structure itself, not just content, shapes AI-generated visual outputs, introducing a new dimension for understanding bias and fairness in multilingual, multimodal systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_03199 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Beyond Content: How Grammatical Gender Shapes Visual Representation in Text-to-Image Models Saeed, Muhammed Raza, Shaina Vayani, Ashmal Abdul-Mageed, Muhammad Emami, Ali Shehata, Shady Computation and Language Research on bias in Text-to-Image (T2I) models has primarily focused on demographic representation and stereotypical attributes, overlooking a fundamental question: how does grammatical gender influence visual representation across languages? We introduce a cross-linguistic benchmark examining words where grammatical gender contradicts stereotypical gender associations (e.g., ``une sentinelle'' - grammatically feminine in French but referring to the stereotypically masculine concept ``guard''). Our dataset spans five gendered languages (French, Spanish, German, Italian, Russian) and two gender-neutral control languages (English, Chinese), comprising 800 unique prompts that generated 28,800 images across three state-of-the-art T2I models. Our analysis reveals that grammatical gender dramatically influences image generation: masculine grammatical markers increase male representation to 73% on average (compared to 22% with gender-neutral English), while feminine grammatical markers increase female representation to 38% (compared to 28% in English). These effects vary systematically by language resource availability and model architecture, with high-resource languages showing stronger effects. Our findings establish that language structure itself, not just content, shapes AI-generated visual outputs, introducing a new dimension for understanding bias and fairness in multilingual, multimodal systems. |
| title | Beyond Content: How Grammatical Gender Shapes Visual Representation in Text-to-Image Models |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2508.03199 |