Breaking Language Barriers or Reinforcing Bias? A Study of Gender and Racial Disparities in Multilingual Contrastive Vision Language Models

• URL: http://arxiv.org/abs/2505.14160v3
• Date: Sun, 26 Oct 2025 21:27:28 GMT
• Title: Breaking Language Barriers or Reinforcing Bias? A Study of Gender and Racial Disparities in Multilingual Contrastive Vision Language Models
• Authors: Zahraa Al Sahili, Ioannis Patras, Matthew Purver,
• Abstract summary: We perform the first systematic audit of four public multilingual CLIP variants: M-CLIP, NLLB-CLIP, CAPIVARA-CLIP, and the debiased SigLIP-2.<n>We quantify race and gender bias and measure stereotype amplification.
• Score: 28.944990804599893
• License: http://creativecommons.org/licenses/by-sa/4.0/
• Abstract: Multilingual vision-language models (VLMs) promise universal image-text retrieval, yet their social biases remain underexplored. We perform the first systematic audit of four public multilingual CLIP variants: M-CLIP, NLLB-CLIP, CAPIVARA-CLIP, and the debiased SigLIP-2, covering ten languages that differ in resource availability and morphological gender marking. Using balanced subsets of FairFace and the PATA stereotype suite in a zero-shot setting, we quantify race and gender bias and measure stereotype amplification. Contrary to the intuition that multilinguality mitigates bias, every model exhibits stronger gender skew than its English-only baseline. CAPIVARA-CLIP shows its largest biases precisely in the low-resource languages it targets, while the shared encoder of NLLB-CLIP and SigLIP-2 transfers English gender stereotypes into gender-neutral languages; loosely coupled encoders largely avoid this leakage. Although SigLIP-2 reduces agency and communion skews, it inherits -- and in caption-sparse contexts (e.g., Xhosa) amplifies -- the English anchor's crime associations. Highly gendered languages consistently magnify all bias types, yet gender-neutral languages remain vulnerable whenever cross-lingual weight sharing imports foreign stereotypes. Aggregated metrics thus mask language-specific hot spots, underscoring the need for fine-grained, language-aware bias evaluation in future multilingual VLM research.

Related papers

• Probing Gender Bias in Multilingual LLMs: A Case Study of Stereotypes in Persian [0.0]
  We propose a template-based probing methodology to uncover gender stereotypes in Multilingual Large Language Models (LLMs)<n>We evaluate four prominent models, focusing on Persian, a low-resource language with distinct linguistic features.<n>Our results show that all models exhibit gender stereotypes, with greater disparities in Persian than in English across all domains.<n>This study underscores the need for inclusive NLP practices and provides a framework for assessing bias in other low-resource languages.
  arXiv  Detail & Related papers  (2025-09-24T14:34:17Z)
• 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)
• Colombian Waitresses y Jueces canadienses: Gender and Country Biases in Occupation Recommendations from LLMs [15.783346695504344]
  We study the first study of multilingual intersecting country and gender biases.<n>We construct a benchmark of prompts in English, Spanish and German, using 25 countries and four pronoun sets.<n>We find that even when models show parity for gender or country individually, intersectional occupational biases based on both country and gender persist.
  arXiv  Detail & Related papers  (2025-05-05T08:40:51Z)
• High-Dimensional Interlingual Representations of Large Language Models [65.77317753001954]
  Large language models (LLMs) trained on massive multilingual datasets hint at the formation of interlingual constructs.<n>We explore 31 diverse languages varying on their resource-levels, typologies, and geographical regions.<n>We find that multilingual LLMs exhibit inconsistent cross-lingual alignments.
  arXiv  Detail & Related papers  (2025-03-14T10:39:27Z)
• 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)
• The Lou Dataset -- Exploring the Impact of Gender-Fair Language in German Text Classification [57.06913662622832]
  Gender-fair language fosters inclusion by addressing all genders or using neutral forms. Gender-fair language substantially impacts predictions by flipping labels, reducing certainty, and altering attention patterns. While we offer initial insights on the effect on German text classification, the findings likely apply to other languages.
  arXiv  Detail & Related papers  (2024-09-26T15:08:17Z)
• Beyond Binary Gender: Evaluating Gender-Inclusive Machine Translation with Ambiguous Attitude Words [85.48043537327258]
  Existing machine translation gender bias evaluations are primarily focused on male and female genders. This study presents a benchmark AmbGIMT (Gender-Inclusive Machine Translation with Ambiguous attitude words) We propose a novel process to evaluate gender bias based on the Emotional Attitude Score (EAS), which is used to quantify ambiguous attitude words.
  arXiv  Detail & Related papers  (2024-07-23T08:13:51Z)
• Leveraging Large Language Models to Measure Gender Representation Bias in Gendered Language Corpora [9.959039325564744]
  Large language models (LLMs) often inherit and amplify social biases embedded in their training data.<n>Gender bias is the association of specific roles or traits with a particular gender.<n>Gender representation bias is the unequal frequency of references to individuals of different genders.
  arXiv  Detail & Related papers  (2024-06-19T16:30:58Z)
• What is Your Favorite Gender, MLM? Gender Bias Evaluation in Multilingual Masked Language Models [8.618945530676614]
  This paper proposes an approach to estimate gender bias in multilingual lexicons from 5 languages: Chinese, English, German, Portuguese, and Spanish. A novel model-based method is presented to generate sentence pairs for a more robust analysis of gender bias. Our results suggest that gender bias should be studied on a large dataset using multiple evaluation metrics for best practice.
  arXiv  Detail & Related papers  (2024-04-09T21:12:08Z)
• 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. We propose a novel benchmark, MAGBIG, intended to foster research on gender bias in multilingual models. 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)
• 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)
• 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)
• Type B Reflexivization as an Unambiguous Testbed for Multilingual Multi-Task Gender Bias [5.239305978984572]
  We show that for languages with type B reflexivization, we can construct multi-task challenge datasets for detecting gender bias. In these languages, the direct translation of 'the doctor removed his mask' is not ambiguous between a coreferential reading and a disjoint reading. We present a multilingual, multi-task challenge dataset, which spans four languages and four NLP tasks.
  arXiv  Detail & Related papers  (2020-09-24T23:47:18Z)
• Gender Bias in Multilingual Embeddings and Cross-Lingual Transfer [101.58431011820755]
  We study gender bias in multilingual embeddings and how it affects transfer learning for NLP applications. We create a multilingual dataset for bias analysis and propose several ways for quantifying bias in multilingual representations.
  arXiv  Detail & Related papers  (2020-05-02T04:34:37Z)
• Multi-Dimensional Gender Bias Classification [67.65551687580552]
  Machine learning models can inadvertently learn socially undesirable patterns when training on gender biased text. We propose a general framework that decomposes gender bias in text along several pragmatic and semantic dimensions. Using this fine-grained framework, we automatically annotate eight large scale datasets with gender information.
  arXiv  Detail & Related papers  (2020-05-01T21:23:20Z)

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.