Beyond Content: How Grammatical Gender Shapes Visual Representation in Text-to-Image Models

• URL: http://arxiv.org/abs/2508.03199v3
• Date: Wed, 01 Oct 2025 10:42:24 GMT
• Title: Beyond Content: How Grammatical Gender Shapes Visual Representation in Text-to-Image Models
• Abstract summary: We introduce a cross-linguistic benchmark examining words where grammatical gender contradicts stereotypical gender associations.<n>Our dataset spans five gendered languages and two gender-neutral control languages.<n> masculine grammatical markers increase male representation to 73% on average, while feminine grammatical markers increase female representation to 38%.
• Score: 40.91012720864256
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• MORPHOGEN: A Multilingual Benchmark for Evaluating Gender-Aware Morphological Generation [12.819315569430293]
  In morphologically rich languages, gender influences verb, pronouns, and even first-person constructions with explicit and implicit mentions of gender.<n>We introduce MORPHOGEN, a morphologically grounded benchmark dataset for evaluating gender-aware generation in three typologically diverse grammatically gendered languages.
  arXiv  Detail & Related papers  (2026-04-20T23:35:24Z)
• EuroGEST: Investigating gender stereotypes in multilingual language models [53.88459905621724]
  Large language models increasingly support multiple languages, yet most benchmarks for gender bias remain English-centric.<n>We introduce EuroGEST, a dataset designed to measure gender-stereotypical reasoning in LLMs across English and 29 European languages.
  arXiv  Detail & Related papers  (2025-06-04T11:58:18Z)
• mGeNTE: A Multilingual Resource for Gender-Neutral Language and Translation [21.461095625903504]
  mGeNTE is a dataset of English-Italian/German/Spanish language pairs.<n>It enables research in both automatic Gender-Neutral Translation (GNT) and language modelling for three grammatical gender languages.
  arXiv  Detail & Related papers  (2025-01-16T09:35:15Z)
• What an Elegant Bridge: Multilingual LLMs are Biased Similarly in Different Languages [51.0349882045866]
  This paper investigates biases of Large Language Models (LLMs) through the lens of grammatical gender. We prompt a model to describe nouns with adjectives in various languages, focusing specifically on languages with grammatical gender. We find that a simple classifier can not only predict noun gender above chance but also exhibit cross-language transferability.
  arXiv  Detail & Related papers  (2024-07-12T22:10:16Z)
• Investigating grammatical abstraction in language models using few-shot learning of novel noun gender [0.0]
  We conduct a noun learning experiment to assess whether an LSTM and a decoder-only transformer can achieve human-like abstraction of grammatical gender in French. We find that both language models effectively generalise novel noun gender from one to two learning examples and apply the learnt gender across agreement contexts. While the generalisation behaviour of models suggests that they represent grammatical gender as an abstract category, like humans, further work is needed to explore the details.
  arXiv  Detail & Related papers  (2024-03-15T14:25:59Z)
• Multilingual Text-to-Image Generation Magnifies Gender Stereotypes and Prompt Engineering May Not Help You [64.74707085021858]
  We show that multilingual models suffer from significant gender biases just as monolingual models do.<n>We propose a novel benchmark, MAGBIG, intended to foster research on gender bias in multilingual models.<n>Our results show that not only do models exhibit strong gender biases but they also behave differently across languages.
  arXiv  Detail & Related papers  (2024-01-29T12:02:28Z)
• VisoGender: A dataset for benchmarking gender bias in image-text pronoun resolution [80.57383975987676]
  VisoGender is a novel dataset for benchmarking gender bias in vision-language models. We focus on occupation-related biases within a hegemonic system of binary gender, inspired by Winograd and Winogender schemas. We benchmark several state-of-the-art vision-language models and find that they demonstrate bias in resolving binary gender in complex scenes.
  arXiv  Detail & Related papers  (2023-06-21T17:59:51Z)
• Gender Lost In Translation: How Bridging The Gap Between Languages Affects Gender Bias in Zero-Shot Multilingual Translation [12.376309678270275]
  bridging the gap between languages for which parallel data is not available affects gender bias in multilingual NMT. We study the effect of encouraging language-agnostic hidden representations on models' ability to preserve gender. We find that language-agnostic representations mitigate zero-shot models' masculine bias, and with increased levels of gender inflection in the bridge language, pivoting surpasses zero-shot translation regarding fairer gender preservation for speaker-related gender agreement.
  arXiv  Detail & Related papers  (2023-05-26T13:51:50Z)
• Don't Forget About Pronouns: Removing Gender Bias in Language Models Without Losing Factual Gender Information [4.391102490444539]
  We focus on two types of such signals in English texts: factual gender information and gender bias. We aim to diminish the stereotypical bias in the representations while preserving the factual gender signal.
  arXiv  Detail & Related papers  (2022-06-21T21:38:25Z)
• Analyzing Gender Representation in Multilingual Models [59.21915055702203]
  We focus on the representation of gender distinctions as a practical case study. We examine the extent to which the gender concept is encoded in shared subspaces across different languages.
  arXiv  Detail & Related papers  (2022-04-20T00:13:01Z)
• Quantifying Gender Bias Towards Politicians in Cross-Lingual Language Models [104.41668491794974]
  We quantify the usage of adjectives and verbs generated by language models surrounding the names of politicians as a function of their gender. We find that while some words such as dead, and designated are associated with both male and female politicians, a few specific words such as beautiful and divorced are predominantly associated with female politicians.
  arXiv  Detail & Related papers  (2021-04-15T15:03:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.