{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T20:54:51Z","timestamp":1781643291154,"version":"3.54.5"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T00:00:00Z","timestamp":1773619200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T00:00:00Z","timestamp":1773619200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Universidade Estadual Paulista J\u00falio De Mesquita Filho"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["AI Ethics"],"published-print":{"date-parts":[[2026,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>This study proposes a multi-layered framework to quantify gender and ethnic bias in state-of-the-art text-to-image models using geographically grounded evaluations across ten American countries. We evaluate Stable Diffusion 1.5, SDXL, Gemini, Flux, and DALL.E by creating two datasets: one organized by race\u2013gender categories and another using only nationality prompts. Using CLIP embeddings, we extract demographic representations through three methods: (i) a KNN classifier trained solely on model-generated demographic exemplars; (ii) a distance-based comparison of country-level embedding centroids to race\u2013gender centroids; and (iii) a semantic layer from a multimodal LLM that infers demographic attributes from each portrait. An autoencoder provides latent-space visualizations for interpretable geometric inspection of cross-country patterns. Across models, we find systematic deviations from real census distributions, including consistent male overrepresentation (except Gemini, which skews female) and strong ethnic homogenization. Latin American countries are repeatedly mapped to Indigenous archetypes, while Canada and the United States are largely rendered with White prototypes. These distortions appear in both embedding geometry and LLM-based semantic judgments, indicating that bias affects low-level visual structure and high-level interpretation. By linking synthetic portraits to demographic baselines, this study offers a scalable method to audit representational fairness in AI models and stresses the need for culturally contextualized evaluation in responsible AI development.<\/jats:p>","DOI":"10.1007\/s43681-026-01066-7","type":"journal-article","created":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T16:15:01Z","timestamp":1773677701000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Bias beyond borders: quantifying gender and ethnic stereotypes across countries in AI image generation"],"prefix":"10.1007","volume":"6","author":[{"given":"Giovanni","family":"Franco","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Regilene Aparecida","family":"Sarzi-Ribeiro","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jo\u00e3o Paulo","family":"Papa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kelton Augusto Pontara","family":"da Costa","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Felipe","family":"Mahlow","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,3,16]]},"reference":[{"key":"1066_CR1","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical Text-Conditional Image Generation with CLIP Latents (2022). arXiv: 2204.06125"},{"key":"1066_CR2","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-Resolution Image Synthesis with Latent Diffusion Models (2022). arXiv: 2112.10752","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"1066_CR3","unstructured":"Podell, D., English, Z., Lacey, K., Blattmann, A., Dockhorn, T., M\u00fcller, J., Penna, J., Rombach, R.: SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis (2023). arXiv: 2307.01952"},{"key":"1066_CR4","unstructured":"Team, G., Anil, R., Borgeaud, S., Alayrac, J.-B., Yu, J., Soricut, R., Schalkwyk, J., Dai, A.M., Hauth, A., Millican, K., et al.: Gemini: a family of highly capable multimodal models. arXiv:2312.11805 (2023)"},{"key":"1066_CR5","unstructured":"Labs, B.F., Batifol, S., Blattmann, A., Boesel, F., Consul, S., Diagne, C., Dockhorn, T., English, J., English, Z., Esser, P., Kulal, S., Lacey, K., Levi, Y., Li, C., Lorenz, D., M\u00fcller, J., Podell, D., Rombach, R., Saini, H., Sauer, A., Smith, L.: FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space (2025). arXiv: 2506.15742"},{"key":"1066_CR6","unstructured":"Ramesh, A., Pavlov, M., Goh, G., Gray, S., Voss, C., Radford, A., Chen, M., Sutskever, I.: Zero-Shot Text-to-Image Generation (2021). arXiv: 2102.12092"},{"key":"1066_CR7","unstructured":"Luccioni, A.S., Akiki, C., Mitchell, M., Jernite, Y.: Stable Bias: Analyzing Societal Representations in Diffusion Models (2023). arXiv: 2303.11408"},{"key":"1066_CR8","doi-asserted-by":"crossref","unstructured":"Crawford, K.: The Atlas of AI: Power, Politics, and the Planetary Costs of Artificial Intelligence. Yale University Press, ??? (2021)","DOI":"10.12987\/9780300252392"},{"issue":"1","key":"1066_CR9","doi-asserted-by":"publisher","first-page":"262","DOI":"10.5753\/jbcs.2025.4166","volume":"31","author":"WA Cruz-Casta\u00f1eda","year":"2025","unstructured":"Cruz-Casta\u00f1eda, W.A., Amadeus, M., Zanella, A.F., Mahlow, F.R.P.: From pampas to pixels: fine-tuning diffusion models for ga\u00facho heritage. J. Braz. Comput. Soc. 31(1), 262\u2013270 (2025)","journal-title":"J. Braz. Comput. Soc."},{"key":"1066_CR10","unstructured":"Birhane, A., Prabhu, V.U., Kahembwe, E.: Multimodal datasets: misogyny, pornography, and malignant stereotypes (2021). arXiv: 2110.01963"},{"issue":"2","key":"1066_CR11","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1007\/s00146-023-01780-4","volume":"40","author":"O Bendel","year":"2025","unstructured":"Bendel, O.: Image synthesis from an ethical perspective. AI & SOCIETY 40(2), 437\u2013446 (2025)","journal-title":"AI & SOCIETY"},{"key":"1066_CR12","unstructured":"Zhou, M., Abhishek, V., Derdenger, T., Kim, J., Srinivasan, K.: Bias in generative ai. arXiv:2403.02726 (2024)"},{"issue":"12","key":"1066_CR13","doi-asserted-by":"publisher","first-page":"1000","DOI":"10.1109\/TLA.2024.10789626","volume":"22","author":"FRP Mahlow","year":"2024","unstructured":"Mahlow, F.R.P., Zanella, A.F., Casta\u00f1eda, W.A.C., Sarzi-Ribeiro, R.A.: Illustrating classic brazilian books using a text-to-image diffusion model. IEEE Lat. Am. Trans. 22(12), 1000\u20131008 (2024)","journal-title":"IEEE Lat. Am. Trans."},{"key":"1066_CR14","doi-asserted-by":"crossref","unstructured":"Wang, W., Bai, H., Huang, J.-T., Wan, Y., Yuan, Y., Qiu, H., Peng, N., Lyu, M.: New job, new gender? measuring the social bias in image generation models. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp. 3781\u20133789 (2024)","DOI":"10.1145\/3664647.3681433"},{"issue":"4","key":"1066_CR15","doi-asserted-by":"publisher","first-page":"2229","DOI":"10.1007\/s00146-024-02129-1","volume":"40","author":"LG Locke","year":"2025","unstructured":"Locke, L.G., Hodgdon, G.: Gender bias in visual generative artificial intelligence systems and the socialization of ai. AI & SOCIETY 40(4), 2229\u20132236 (2025)","journal-title":"AI & SOCIETY"},{"key":"1066_CR16","unstructured":"Girrbach, L., Alaniz, S., Smith, G., Akata, Z.: A Large Scale Analysis of Gender Biases in Text-to-Image Generative Models (2025). arXiv: 2503.23398"},{"issue":"2","key":"1066_CR17","doi-asserted-by":"publisher","first-page":"35","DOI":"10.3390\/jimaging11020035","volume":"11","author":"Y Wu","year":"2025","unstructured":"Wu, Y., Nakashima, Y., Garcia, N.: Revealing gender bias from prompt to image in stable diffusion. J. Imaging 11(2), 35 (2025)","journal-title":"J. Imaging"},{"key":"1066_CR18","doi-asserted-by":"crossref","unstructured":"D\u2019Inc\u00e0, M., Peruzzo, E., Mancini, M., Xu, D., Goel, V., Xu, X., Wang, Z., Shi, H., Sebe, N.: OpenBias: Open-set Bias Detection in Text-to-Image Generative Models (2024). arXiv: 2404.07990","DOI":"10.1109\/CVPR52733.2024.01162"},{"key":"1066_CR19","unstructured":"Vice, J., Akhtar, N., Hartley, R., Mian, A.: Exploring Bias in over 100 Text-to-Image Generative Models (2025). arXiv: 2503.08012"},{"key":"1066_CR20","doi-asserted-by":"crossref","unstructured":"Sufian, A., Distante, C., Leo, M., Salam, H.: T2IBias: Uncovering Societal Bias Encoded in the Latent Space of Text-to-Image Generative Models (2025). arXiv: 2511.10089","DOI":"10.1007\/978-3-032-16886-3_4"},{"key":"1066_CR21","doi-asserted-by":"crossref","unstructured":"Nadeem, M., Sohail, S.S., Cambria, E., Schuller, B.W., Hussain, A.: Gender Bias in Text-to-Video Generation Models: A case study of Sora (2025). arXiv: 2501.01987","DOI":"10.1109\/MIS.2025.3561475"},{"key":"1066_CR22","doi-asserted-by":"crossref","unstructured":"Nakamura, Y., Sato, K., Suzuki, A., Tanaka, H.: Cross-modal bias transfer in aligned video diffusion models. Preprints (2026) 10.20944\/preprints202601.1956.v1","DOI":"10.20944\/preprints202601.1956.v1"},{"key":"1066_CR23","unstructured":"Hall, M., Ross, C., Williams, A., Carion, N., Drozdzal, M., Soriano, A.R.: DIG. In: Evaluating Disparities in Image Generations with Indicators for Geographic Diversity (2024). arXiv: 2308.06198"},{"key":"1066_CR24","unstructured":"Sureddy, A., Padalia, D., Periyakaruppa, N., Saha, O., Williams, A., Romero-Soriano, A., Richards, M., Kirichenko, P., Hall, M.: Decomposed evaluations of geographic disparities in text-to-image models (2024). arXiv: 2406.11988"},{"key":"1066_CR25","doi-asserted-by":"crossref","unstructured":"Basu, A., Babu, R.V., Pruthi, D.: Inspecting the Geographical Representativeness of Images from Text-to-Image Models (2023). arXiv: 2305.11080","DOI":"10.1109\/ICCV51070.2023.00474"},{"key":"1066_CR26","doi-asserted-by":"crossref","unstructured":"Friedrich, F., H\u00e4mmerl, K., Schramowski, P., Brack, M., Libovicky, J., Kersting, K., Fraser, A.: Multilingual Text-to-Image Generation Magnifies Gender Stereotypes and Prompt Engineering May Not Help You (2025). arXiv: 2401.16092","DOI":"10.18653\/v1\/2025.acl-long.966"},{"key":"1066_CR27","doi-asserted-by":"crossref","unstructured":"Wolfe, R., Caliskan, A.: American == White in Multimodal Language-and-Image AI (2022). arXiv: 2207.00691","DOI":"10.1145\/3514094.3534136"},{"key":"1066_CR28","unstructured":"Seo, H., Choi, S., Hong, M., Zhou, Y., Kim, J., Ismaila, L., Etori, N., Agarwal, M., Liu, Z., Kim, J., Oh, J.: Exposing Blindspots: Cultural Bias Evaluation in Generative Image Models (2025). arXiv: 2510.20042"},{"key":"1066_CR29","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., Krueger, G., Sutskever, I.: Learning Transferable Visual Models From Natural Language Supervision (2021). arXiv: 2103.00020"},{"key":"1066_CR30","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"7825","key":"1066_CR31","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1038\/s41586-020-2649-2","volume":"585","author":"CR Harris","year":"2020","unstructured":"Harris, C.R., Millman, K.J., Walt, S.J., Gommers, R., Virtanen, P., Cournapeau, D., Wieser, E., Taylor, J., Berg, S., Smith, N.J., Kern, R., Picus, M., Hoyer, S., Kerkwijk, M.H., Brett, M., Haldane, A., R\u00edo, J.F., Wiebe, M., Peterson, P., G\u00e9rard-Marchant, P., Sheppard, K., Reddy, T., Weckesser, W., Abbasi, H., Gohlke, C., Oliphant, T.E.: Array programming with NumPy. Nature 585(7825), 357\u2013362 (2020). https:\/\/doi.org\/10.1038\/s41586-020-2649-2","journal-title":"Nature"},{"key":"1066_CR32","doi-asserted-by":"crossref","unstructured":"Fix, E., Hodges, J.L.: Discriminatory analysis. nonparametric discrimination: Consistency properties. International Statistical Review \/ Revue Internationale de Statistique 57(3), 238\u2013247 (1989). Accessed 2025\u201311-26","DOI":"10.2307\/1403797"},{"key":"1066_CR33","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., Vanderplas, J., Passos, A., Cournapeau, D., Brucher, M., Perrot, M., Duchesnay, E.: Scikit-learn: Machine learning in Python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"1066_CR34","unstructured":"Yang, A., Li, A., Yang, B., Zhang, B., Hui, B., Zheng, B., Yu, B., Gao, C., Huang, C., Lv, C., Zheng, C., Liu, D., Zhou, F., Huang, F., Hu, F., Ge, H., Wei, H., Lin, H., Tang, J., Yang, J., Tu, J., Zhang, J., Yang, J., Yang, J., Zhou, J., Zhou, J., Lin, J., Dang, K., Bao, K., Yang, K., Yu, L., Deng, L., Li, M., Xue, M., Li, M., Zhang, P., Wang, P., Zhu, Q., Men, R., Gao, R., Liu, S., Luo, S., Li, T., Tang, T., Yin, W., Ren, X., Wang, X., Zhang, X., Ren, X., Fan, Y., Su, Y., Zhang, Y., Zhang, Y., Wan, Y., Liu, Y., Wang, Z., Cui, Z., Zhang, Z., Zhou, Z., Qiu, Z.: Qwen3 Technical Report (2025). arXiv: 2505.09388"},{"key":"1066_CR35","doi-asserted-by":"crossref","unstructured":"Rumelhart, D.E., Hinton, G.E., Williams, R.J.: Learning representations by back-propagating errors. nature 323(6088), 533\u2013536 (1986)","DOI":"10.1038\/323533a0"},{"key":"1066_CR36","unstructured":"Maaten, L., Hinton, G.: Visualizing data using t-sne. Journal of machine learning research 9(11) (2008)"},{"key":"1066_CR37","doi-asserted-by":"crossref","unstructured":"McInnes, L., Healy, J., Melville, J.: Umap: Uniform manifold approximation and projection for dimension reduction. arXiv:1802.03426 (2018)","DOI":"10.21105\/joss.00861"},{"key":"1066_CR38","unstructured":"U.S. Census Bureau: (2020) Census: Key Statistics on Race, Hispanic Origin, and the Population of the United States. https:\/\/www.census.gov\/library\/publications\/2021\/dec\/2020-census-key-statistics.html (2021)"},{"key":"1066_CR39","unstructured":"(IBGE), I.: Censo Demogr\u00e1fico (2022): Resultados de Cor ou Ra\u00e7a - Caracter\u00edsticas Gerais da Popula\u00e7\u00e3o. https:\/\/www.ibge.gov.br\/estatisticas\/sociais\/populacao\/22827-censo-demografico-2022.html (2022)"},{"key":"1066_CR40","unstructured":"(INDEC), I.: Censo Nacional de Poblaci\u00f3n, Hogares y Viviendas 2022 (CNPHV 2022): Resultados Definitivos sobre Autoidentificaci\u00f3n \u00c9tnica. https:\/\/www.indec.gob.ar\/indec\/web\/Nivel3-Tema-2-41 (2022)"},{"key":"1066_CR41","unstructured":"(INE), I.: Radiograf\u00eda de G\u00e9nero: Pueblos Originarios en Chile 2017. https:\/\/www.ine.gob.cl\/docs\/default-source\/genero\/documentos-de-an%C3%A1lisis\/documentos\/radiografia-de-genero-pueblos-originarios-chile2017.pdf (2017)"},{"key":"1066_CR42","unstructured":"(DANE), D.: Censo Nacional de Poblaci\u00f3n y Vivienda 2018 (CNPV 2018): Resultados de Autorreconocimiento \u00c9tnico. https:\/\/www.dane.gov.co\/index.php\/estadisticas-por-tema\/enfoque-diferencial-e-interseccional\/autorreconocimiento-etnico (2018)"},{"key":"1066_CR43","unstructured":"(INE), I.: Censo Nacional de Poblaci\u00f3n y Vivienda 2011: Resultados sobre Autoidentificaci\u00f3n \u00c9tnica. https:\/\/saludindigena.files.wordpress.com\/2013\/10\/primerosresultadosindigena2011.pdf (2011)"},{"key":"1066_CR44","doi-asserted-by":"publisher","unstructured":"Guzm\u00e1n, M.G.R., Blanco, T.N.: Self-rated health and sociodemographic inequalities among venezuelan adults: a study based on the national survey of living conditions (encovi 2021). Cad. Saude Publica 40(6), 00149323 (2024). https:\/\/doi.org\/10.1590\/0102-311XEN149323. Notes the use of 2011 census weights as the necessary standard for population calibration in the absence of more recent granular data","DOI":"10.1590\/0102-311XEN149323"},{"key":"1066_CR45","doi-asserted-by":"publisher","unstructured":"Villamizar-Chaparro, M.: The demography of crisis-driven outflows from venezuela. Popul. Dev. Rev. 50(2), 321\u2013345 (2024). https:\/\/doi.org\/10.1111\/padr.12613. Discusses demographic adjustments using the 2011 census as the last complete baseline due to the limited accessibility of subsequent official data","DOI":"10.1111\/padr.12613"},{"key":"1066_CR46","unstructured":"(StatCan), S.: Census Profile, (2021) Census of Population: Canada. https:\/\/www12.statcan.gc.ca\/census-recensement\/2021\/dp-pd\/prof\/details\/page.cfm?Lang=E&TABID=1&Details=1&Code1=01&Code2=1&SearchText=Canada&SearchType=Begins&SearchPR=01&B1=All (2021)"},{"key":"1066_CR47","unstructured":"(INE), I.: Censo Nacional de Poblaci\u00f3n y Vivienda 2018: Resultados de Pertenencia a Pueblo y G\u00c9nero. https:\/\/www.ine.gob.gt\/sistema\/uploads\/2021\/02\/10\/e844b36056341270f2f36087955c4d53.pdf (2018)"},{"key":"1066_CR48","unstructured":"(INEI), I.: Censo Nacional de Poblaci\u00f3n, Hogares y Vivienda 2017: Caracter\u00edsticas de la Poblaci\u00f3n. https:\/\/www.inei.gob.pe\/media\/MenuRecursivo\/publicaciones_digitales\/Est\/Lib1530\/Censo2017_Caracteristicas%20de%20la%20poblacion.pdf (2017)"},{"key":"1066_CR49","unstructured":"(INEGI), I.: Censo de Poblaci\u00f3n y Vivienda 2020: Poblaci\u00f3n Ind\u00edgena y Afrodescendiente. https:\/\/www.inegi.org.mx\/programas\/ccpv\/2020\/ (2020)"}],"container-title":["AI and Ethics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s43681-026-01066-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s43681-026-01066-7","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s43681-026-01066-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T20:13:29Z","timestamp":1781640809000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s43681-026-01066-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,16]]},"references-count":49,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,4]]}},"alternative-id":["1066"],"URL":"https:\/\/doi.org\/10.1007\/s43681-026-01066-7","relation":{},"ISSN":["2730-5953","2730-5961"],"issn-type":[{"value":"2730-5953","type":"print"},{"value":"2730-5961","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,16]]},"assertion":[{"value":"29 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 February 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"16 March 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"The authors declare no Conflict of interest.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"203"}}