{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,10]],"date-time":"2026-05-10T10:28:46Z","timestamp":1778408926980,"version":"3.51.4"},"reference-count":115,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3585745","type":"journal-article","created":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T13:29:56Z","timestamp":1751549396000},"page":"122636-122659","source":"Crossref","is-referenced-by-count":9,"title":["Cultural Bias in Text-to-Image Models: A Systematic Review of Bias Identification, Evaluation, and Mitigation Strategies"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1933-3254","authenticated-orcid":false,"given":"Wala","family":"Elsharif","sequence":"first","affiliation":[{"name":"ICT Division, College of Science and Engineering, Hamad Bin Khalifa University, Ar Rayyan, Qatar"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6082-7873","authenticated-orcid":false,"given":"Mahmood","family":"Alzubaidi","sequence":"additional","affiliation":[{"name":"ICT Division, College of Science and Engineering, Hamad Bin Khalifa University, Ar Rayyan, Qatar"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2752-3525","authenticated-orcid":false,"given":"Marco","family":"Agus","sequence":"additional","affiliation":[{"name":"ICT Division, College of Science and Engineering, Hamad Bin Khalifa University, Ar Rayyan, Qatar"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ramesh"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3581641.3584078"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3282067"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00727"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1080\/14626268.2023.2174557"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3611025"},{"key":"ref7","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Saharia"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01213"},{"key":"ref9","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1001\/jamadermatol.2021.3129"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/bdcc7010015"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3600211.3604722"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3637549"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.nlp.2023.100047"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICSTSN61422.2024.10671230"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ISTAS61960.2024.10732696"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_179771"},{"key":"ref19","article-title":"LAION-400M: Open dataset of CLIP-filtered 400 million image-text pairs","author":"Schuhmann","year":"2021","journal-title":"arXiv:2111.02114"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463257"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref22","article-title":"Large scale GAN training for high fidelity natural image synthesis","author":"Brock","year":"2018","journal-title":"arXiv:1809.11096"},{"key":"ref23","article-title":"Hierarchical text-conditional image generation with CLIP latents","author":"Ramesh","year":"2022","journal-title":"arXiv:2204.06125"},{"key":"ref24","first-page":"25278","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Schuhmann"},{"key":"ref25","volume-title":"Stable Diffusion 2","year":"2022"},{"key":"ref26","article-title":"SDXL: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023","journal-title":"arXiv:2307.01952"},{"key":"ref27","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"ref29","article-title":"Scaling autoregressive models for content-rich text-to-image generation","author":"Yu","year":"2022","journal-title":"arXiv:2206.10789"},{"key":"ref30","volume-title":"DeepFloyd IF: A Novel State-of-the-Art Open-Source Text-to-Image Model With a High Degree of Photorealism and Language Understanding","year":"2023"},{"issue":"3","key":"ref31","first-page":"8","article-title":"Improving image generation with better captions","volume":"2","author":"Betker","year":"2023","journal-title":"Comput. Sci."},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref33","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Brown"},{"issue":"140","key":"ref34","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2019","journal-title":"J. Mach. Learn. Res."},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00143"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.629"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1561\/2200000056"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45855.2022.9839249"},{"key":"ref40","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv:2112.10741"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_6"},{"key":"ref42","volume-title":"The Oxford Review - Organisational & Leadership Research","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_179932"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1211286109"},{"key":"ref45","volume-title":"Racial Bias","year":"2017"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1111\/ans.18792"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.bjae.2021.11.011"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1111\/j.0021-9029.2006.00062.x"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.4324\/9780429500480-5"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1080\/13674580000200100"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.erap.2003.12.004"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.23947\/2414-1143-2018-15-3-23-29"},{"key":"ref53","article-title":"Analysing gender bias in text-to-image models using object detection","author":"Mannering","year":"2023","journal-title":"arXiv:2307.08025"},{"key":"ref54","article-title":"Analyzing quality, bias, and performance in text-to-image generative models","author":"Masrourisaadat","year":"2024","journal-title":"arXiv:2407.00138"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/799"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1001\/jamasurg.2023.5695"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1186\/s13054-024-05134-4"},{"key":"ref58","article-title":"FAIntbench: A holistic and precise benchmark for bias evaluation in text-to-image models","author":"Luo","year":"2024","journal-title":"arXiv:2405.17814"},{"key":"ref59","article-title":"GradBias: Unveiling word influence on bias in text-to-image generative models","author":"D\u2019Inc\u00e0","year":"2024","journal-title":"arXiv:2408.16700"},{"key":"ref60","first-page":"56338","article-title":"Stable bias: Evaluating societal representations in diffusion models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Luccioni"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3593013.3594095"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00840"},{"key":"ref63","article-title":"MIST: Mitigating intersectional bias with disentangled cross-attention editing in text-to-image diffusion models","author":"Yesiltepe","year":"2024","journal-title":"arXiv:2403.19738"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681652"},{"key":"ref65","article-title":"Backdooring bias into text-to-image models","author":"Naseh","year":"2024","journal-title":"arXiv:2406.15213"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/659"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680748"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.3233\/FAIA240581"},{"key":"ref69","article-title":"BIGbench: A unified benchmark for evaluating multi-dimensional social biases in text-to-image models","author":"Luo","year":"2024","journal-title":"arXiv:2407.15240"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.66"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME58846.2023.00051"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1136\/bmjment-2024-301298"},{"key":"ref73","article-title":"Decomposed evaluations of geographic disparities in text-to-image models","author":"Sureddy","year":"2024","journal-title":"arXiv:2406.11988"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642877"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.gebnlp-1.21"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/3649217.3653596"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72986-7_25"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01162"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00283"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.160"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.353"},{"key":"ref82","volume-title":"Training unbiased diffusion models from biased dataset. In The Twelfth International Conference on Learning Representations","author":"Kim","year":"2024"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.3390\/info15100594"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICAIC60265.2024.10433840"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/3658644.3690288"},{"key":"ref86","article-title":"The male CEO and the female assistant: Evaluation and mitigation of gender biases in text-to-image generation of dual subjects","author":"Wan","year":"2024","journal-title":"arXiv:2402.11089"},{"key":"ref87","article-title":"Can prompt modifiers control bias? A comparative analysis of text-to-image generative models","author":"Wootaek Shin","year":"2024","journal-title":"arXiv:2406.05602"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611994"},{"key":"ref89","article-title":"Word-level explanations for analyzing bias in text-to-image models","author":"Lin","year":"2023","journal-title":"arXiv:2306.05500"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1609\/aies.v7i1.31652"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i13.29403"},{"key":"ref92","first-page":"69981","article-title":"Holistic evaluation of text-to-image models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Lee"},{"key":"ref93","article-title":"Quantifying bias in text-to-image generative models","author":"Vice","year":"2023","journal-title":"arXiv:2312.13053"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1145\/3600211.3604711"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1145\/3628516.3659404"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jchemed.4c00249"},{"key":"ref97","article-title":"Bias begets bias: The impact of biased embeddings on diffusion models","author":"Kuchlous","year":"2024","journal-title":"arXiv:2409.09569"},{"key":"ref98","article-title":"Failures are fated, but can be faded: Characterizing and mitigating unwanted behaviors in large-scale vision and language models","author":"Sagar","year":"2024","journal-title":"arXiv:2406.07145"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72855-6_27"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1093\/ijpp\/riae049"},{"key":"ref101","article-title":"How do generative models draw a software engineer? A case study on stable diffusion bias","author":"Fadahunsi","year":"2025","journal-title":"arXiv:2501.09014"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1145\/3641237.3691658"},{"key":"ref103","article-title":"Religious bias landscape in language and text-to-image models: Analysis, detection, and debiasing strategies","author":"Abrar","year":"2025","journal-title":"arXiv:2501.08441"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1093\/jcmc\/zmad045"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.667"},{"key":"ref106","article-title":"Mitigating stereotypical biases in text to image generative systems","author":"Esposito","year":"2023","journal-title":"arXiv:2310.06904"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.14778\/3681954.3682014"},{"key":"ref108","article-title":"InvDiff: Invariant guidance for bias mitigation in diffusion models","author":"Hou","year":"2024","journal-title":"arXiv:2412.08480"},{"key":"ref109","article-title":"MoESD: Mixture of experts stable diffusion to mitigate gender bias","author":"Wang","year":"2024","journal-title":"arXiv:2407.11002"},{"key":"ref110","first-page":"8385","article-title":"Are diffusion models vision-and-language reasoners?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Krojer"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12143066"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00296"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1177\/00178969241274621"},{"key":"ref114","article-title":"VLBiasBench: A comprehensive benchmark for evaluating bias in large vision-language model","author":"Wang","year":"2024","journal-title":"arXiv:2406.14194"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR62202.2024.00071"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11071263.pdf?arnumber=11071263","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,26]],"date-time":"2025-07-26T06:29:21Z","timestamp":1753511361000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11071263\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":115,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3585745","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}