mlsanityData to 7 Oct 2026

Text-to-Image Models and Their Representation of People from Different Nationalities Engaging in Activities

arXiv 2504.06313 ↗First posted 8 Apr 2025cs.CV cs.CYcited by 0

Not on the map. Why?

Abstract (arXiv)

This paper investigates how popular text-to-image (T2I) models, DALL-E 3 and Gemini 3 Pro Preview, depict people from 206 nationalities when prompted to generate images of individuals engaging in common everyday activities. Five scenarios were developed, and 2,060 images were generated using input prompts that specified nationalities across five activities. When aggregating across activities and models, results showed that 28.4% of the images depicted individuals wearing traditional attire, including attire that is impractical for the specified activities in several cases. This pattern was statistically significantly associated with regions, with the Middle East & North Africa and Sub-Saharan Africa disproportionately affected, and was also associated with World Bank income groups. Similar region- and income-linked patterns were observed for images labeled as depicting impractical attire in two athletics-related activities. To assess image-text alignment, CLIP, ALIGN, and GPT-4.1 mini were used to score 9,270 image-prompt pairs. Images labeled as featuring traditional attire received statistically significantly higher alignment scores when prompts included country names, and this pattern weakened or reversed when country names were removed. Revised prompt analysis showed that one model frequently inserted the word "traditional" (50.3% for traditional-labeled images vs. 16.6% otherwise). These results indicate that these representational patterns can be shaped by several components of the pipeline, including image generator, evaluation models, and prompt revision.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 47 of its 70 references that are in the map. First posted on arXiv 8 Apr 2025.

Builds on

47 of 70 references.

References · 47

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,049
  3. 2021Scaling Up Visual and Vision-Language Representation Learning With Noisy Text Supervisioncited by 3,848
  4. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  5. 2024Evaluating Text-to-Visual Generation with Image-to-Text Generationcited by 465
  6. 2022Easily Accessible Text-to-Image Generation Amplifies Demographic Stereotypes at Large Scalecited by 262
  7. 2022DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Modelscited by 230
  8. 2023Stable Bias: Analyzing Societal Representations in Diffusion Modelscited by 225
  9. 2019A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cyclecited by 192
  10. 2023Alpha-CLIP: A CLIP Model Focusing on Wherever You Wantcited by 150
  11. 2020REVISE: A Tool for Measuring and Mitigating Bias in Visual Datasetscited by 136
  12. 2023Holistic Analysis of Hallucination in GPT-4V(ision): Bias and Interference Challengescited by 131
35 more
  1. 2021Evaluating CLIP: Towards Characterization of Broader Capabilities and Downstream Implicationscited by 128
  2. 2024Survey of Cultural Awareness in Language Models: Text and Beyondcited by 101
  3. 2020Decolonial AI: Decolonial Theory as Sociotechnical Foresight in Artificial Intelligencecited by 100
  4. 2024Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigationcited by 66
  5. 2023ITI-GEN: Inclusive Text-to-Image Generationcited by 64
  6. 2024OpenBias: Open-set Bias Detection in Text-to-Image Generative Modelscited by 61
  7. 2023AI's Regimes of Representation: A Community-centered Study of Text-to-Image Models in South Asiacited by 54
  8. 2024VHELM: A Holistic Evaluation of Vision Language Modelscited by 53
  9. 2023Inspecting the Geographical Representativeness of Images from Text-to-Image Modelscited by 44
  10. 2024An image speaks a thousand words, but can everyone listen? On image transcreation for cultural relevancecited by 36
  11. 2023Divide, Evaluate, and Refine: Evaluating and Improving Text-to-Image Alignment with Iterative VQA Feedbackcited by 31
  12. 2024Beyond Aesthetics: Cultural Competence in Text-to-Image Modelscited by 30
  13. 2024AI for social science and social science of AI: A Surveycited by 29
  14. 2024ViSAGe: A Global-Scale Analysis of Visual Stereotypes in Text-to-Image Generationcited by 27
  15. 2024Culturally Aware and Adapted NLP: A Taxonomy and a Survey of the State of the Artcited by 26
  16. 2024Do Generative AI Models Output Harm while Representing Non-Western Cultures: Evidence from A Community-Centered Approachcited by 25
  17. 2024SeeGULL Multilingual: a Dataset of Geo-Culturally Situated Stereotypescited by 24
  18. 2024Improving Geo-diversity of Generated Images with Contextualized Vendi Score Guidancecited by 24
  19. 2024The Dark Side of Dataset Scaling: Evaluating Racial Classification in Multimodal Modelscited by 23
  20. 2023Navigating Cultural Chasms: Exploring and Unlocking the Cultural POV of Text-To-Image Modelscited by 16
  21. 2024Towards Geographic Inclusion in the Evaluation of Text-to-Image Modelscited by 16
  22. 2025The Case for "Thick Evaluations" of Cultural Representation in AIcited by 16
  23. 2023Bridging the Digital Divide: Performance Variation across Socio-Economic Factors in Vision-Language Modelscited by 11
  24. 2024Image2Text2Image: A Novel Framework for Label-Free Evaluation of Image-to-Text Generation with Text-to-Image Diffusion Modelscited by 10
  25. 2023DIG In: Evaluating Disparities in Image Generations with Indicators for Geographic Diversitycited by 9
  26. 2024"I Searched for a Religious Song in Amharic and Got Sexual Content Instead": Investigating Online Harm in Low-Resourced Languages on YouTubecited by 9
  27. 2024Analyzing Quality, Bias, and Performance in Text-to-Image Generative Modelscited by 9
  28. 2024The Power of Many: Multi-Agent Multimodal Models for Cultural Image Captioningcited by 9
  29. 2025Risks of Cultural Erasure in Large Language Modelscited by 9
  30. 2025Exploring Bias in over 100 Text-to-Image Generative Modelscited by 9
  31. 2025OASIS Uncovers: High-Quality T2I Models, Same Old Stereotypescited by 8
  32. 2025Culture-TRIP: Culturally-Aware Text-to-Image Generation with Iterative Prompt Refinementcited by 7
  33. 2021Similarities between Arabic Dialects: Investigating Geographical Proximitycited by 5
  34. 2024EvalGIM: A Library for Evaluating Generative Image Modelscited by 5
  35. 2024Rethinking Sparse Lexical Representations for Image Retrieval in the Age of Rising Multi-Modal Large Language Modelscited by 2

Built on by

Not cited yet.