# Multilingual Text-to-Image Generation Magnifies Gender Stereotypes and Prompt Engineering May Not Help You

arXiv: https://arxiv.org/abs/2401.16092 · HTML: https://mlsanity.com/paper/2401.16092/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 44 of its 78 references that are in the map.
- First posted on arXiv 29 Jan 2024.

## Builds on (most cited first, 30 of 44)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [Man is to Computer Programmer as Woman is to Homemaker? Debiasing Word Embeddings](https://mlsanity.com/paper/1607.06520/) (2016)
- [Semantics derived automatically from language corpora contain human-like biases](https://mlsanity.com/paper/1608.07187/) (2016)
- [Gender Bias in Coreference Resolution: Evaluation and Debiasing Methods](https://mlsanity.com/paper/1804.06876/) (2018)
- [Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models](https://mlsanity.com/paper/2211.05105/) (2022)
- [Gender Bias in Coreference Resolution](https://mlsanity.com/paper/1804.09301/) (2018)
- [Massively Multilingual Sentence Embeddings for Zero-Shot Cross-Lingual Transfer and Beyond](https://mlsanity.com/paper/1812.10464/) (2018)
- [Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scale](https://mlsanity.com/paper/2211.03759/) (2022)
- [Evaluating Gender Bias in Machine Translation](https://mlsanity.com/paper/1906.00591/) (2019)
- [Towards Robust Blind Face Restoration with Codebook Lookup Transformer](https://mlsanity.com/paper/2206.11253/) (2022)
- [DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models](https://mlsanity.com/paper/2202.04053/) (2022)
- [Stable Bias: Analyzing Societal Representations in Diffusion Models](https://mlsanity.com/paper/2303.11408/) (2023)
- [FairGAN: Fairness-aware Generative Adversarial Networks](https://mlsanity.com/paper/1805.11202/) (2018)
- [Holistic Evaluation of Text-To-Image Models](https://mlsanity.com/paper/2311.04287/) (2023)
- [SimAlign: High Quality Word Alignments without Parallel Training Data using Static and Contextualized Embeddings](https://mlsanity.com/paper/2004.08728/) (2020)
- [Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness](https://mlsanity.com/paper/2302.10893/) (2023)
- [Fairness in Machine Learning: Lessons from Political Philosophy](https://mlsanity.com/paper/1712.03586/) (2017)
- [Debiasing Vision-Language Models via Biased Prompts](https://mlsanity.com/paper/2302.00070/) (2023)
- [Evaluating CLIP: Towards Characterization of Broader Capabilities and Downstream Implications](https://mlsanity.com/paper/2108.02818/) (2021)
- [Social Biases through the Text-to-Image Generation Lens](https://mlsanity.com/paper/2304.06034/) (2023)
- [It's All in the Name: Mitigating Gender Bias with Name-Based Counterfactual Data Substitution](https://mlsanity.com/paper/1909.00871/) (2019)
- [50 Years of Test (Un)fairness: Lessons for Machine Learning](https://mlsanity.com/paper/1811.10104/) (2018)
- [How well can Text-to-Image Generative Models understand Ethical Natural Language Interventions?](https://mlsanity.com/paper/2210.15230/) (2022)
- [AltCLIP: Altering the Language Encoder in CLIP for Extended Language Capabilities](https://mlsanity.com/paper/2211.06679/) (2022)
- [Unmasking Contextual Stereotypes: Measuring and Mitigating BERT's Gender Bias](https://mlsanity.com/paper/2010.14534/) (2020)

## Built on by (most cited first, 15 of 15)

- [Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation](https://mlsanity.com/paper/2404.01030/) (2024)
- [LlavaGuard: An Open VLM-based Framework for Safeguarding Vision Datasets and Models](https://mlsanity.com/paper/2406.05113/) (2024)
- [Text-to-Image Synthesis: A Decade Survey](https://mlsanity.com/paper/2411.16164/) (2024)
- [LLMs Lost in Translation: M-ALERT uncovers Cross-Linguistic Safety Inconsistencies](https://mlsanity.com/paper/2412.15035/) (2024)
- [The Factuality Tax of Diversity-Intervened Text-to-Image Generation: Benchmark and Fact-Augmented Intervention](https://mlsanity.com/paper/2407.00377/) (2024)
- [Navigating Text-to-Image Generative Bias across Indic Languages](https://mlsanity.com/paper/2408.00283/) (2024)
- [How to Train your Text-to-Image Model: Evaluating Design Choices for Synthetic Training Captions](https://mlsanity.com/paper/2506.16679/) (2025)
- [Do Existing Testing Tools Really Uncover Gender Bias in Text-to-Image Models?](https://mlsanity.com/paper/2501.15775/) (2025)
- [Generated Bias: Auditing Internal Bias Dynamics of Text-To-Image Generative Models](https://mlsanity.com/paper/2410.07884/) (2024)
- [Reflexive Prompt Engineering: A Framework for Responsible Prompt Engineering and Interaction Design](https://mlsanity.com/paper/2504.16204/) (2025)
- [NeoBabel: A Multilingual Open Tower for Visual Generation](https://mlsanity.com/paper/2507.06137/) (2025)
- [The Cake that is Intelligence and Who Gets to Bake it: An AI Analogy and its Implications for Participation](https://mlsanity.com/paper/2502.03038/) (2025)
- [Order Is Not Layout: Order-to-Space Bias in Image Generation](https://mlsanity.com/paper/2603.03714/) (2026)
- [SoS: Analysis of Surface over Semantics in Multilingual Text-To-Image Generation](https://mlsanity.com/paper/2601.16803/) (2026)
- [BAFIS: Dataset + Framework to assess occupational Bias and Human Preference in modern Text-to-image Models](https://mlsanity.com/paper/2606.20241/) (2026)

## Abstract (arXiv)

Text-to-image generation models have recently achieved astonishing results in image quality, flexibility, and text alignment, and are consequently employed in a fast-growing number of applications. Through improvements in multilingual abilities, a larger community now has access to this technology. However, our results show that multilingual models suffer from significant gender biases just as monolingual models do. Furthermore, the natural expectation that multilingual models will provide similar results across languages does not hold up. Instead, there are important differences between languages. We propose a novel benchmark, MAGBIG, intended to foster research on gender bias in multilingual models. We use MAGBIG to investigate the effect of multilingualism on gender bias in T2I models. To this end, we construct multilingual prompts requesting portraits of people with a certain occupation or trait. Our results show that not only do models exhibit strong gender biases but they also behave differently across languages. Furthermore, we investigate prompt engineering strategies, such as indirect, neutral formulations, to mitigate these biases. Unfortunately, these approaches have limited success and result in worse text-to-image alignment. Consequently, we call for more research into diverse representations across languages in image generators, as well as into steerability to address biased model behavior.