mlsanityData to 14 Oct 2026

Diffusion Models Through a Global Lens: Are They Culturally Inclusive?

arXiv 2502.08914 ↗First posted 13 Feb 2025cs.CV cs.AIcited by 14

On the map: Diffusion models → Image generation, text-to-image and editing

Abstract (arXiv)

Text-to-image diffusion models have recently enabled the creation of visually compelling, detailed images from textual prompts. However, their ability to accurately represent various cultural nuances remains an open question. In our work, we introduce CultDiff benchmark, evaluating state-of-the-art diffusion models whether they can generate culturally specific images spanning ten countries. We show that these models often fail to generate cultural artifacts in architecture, clothing, and food, especially for underrepresented country regions, by conducting a fine-grained analysis of different similarity aspects, revealing significant disparities in cultural relevance, description fidelity, and realism compared to real-world reference images. With the collected human evaluations, we develop a neural-based image-image similarity metric, namely, CultDiff-S, to predict human judgment on real and generated images with cultural artifacts. Our work highlights the need for more inclusive generative AI systems and equitable dataset representation over a wide range of cultures.

Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Placed in Image generation, text-to-image and editing, one of 14 directions in Diffusion models. Builds on 38 of its 58 references that are in the map. First posted on arXiv 13 Feb 2025.

Builds on

38 of 58 references.

Closest ancestors · 7

Same direction, newest first

  1. 2024Draw Like an Artist: Complex Scene Generation with Diffusion Model via Composition, Painting, and Retouching25 Aug
  2. 2023On quantifying and improving realism of images generated with diffusion26 Sep
  3. 2023StyleDiffusion: Controllable Disentangled Style Transfer via Diffusion Models15 Aug
  4. 2022Inversion-Based Style Transfer with Diffusion Models23 Nov
  5. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation25 Aug
  6. 2022Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding23 May
  7. 2022Hierarchical Text-Conditional Image Generation with CLIP Latents13 Apr

Other references · 31

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 30,186
  2. 2022Training language models to follow instructions with human feedbackcited by 15,971
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  4. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,968
  5. 2023SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesiscited by 4,356
  6. 2024Scaling Rectified Flow Transformers for High-Resolution Image Synthesiscited by 4,181
  7. 2016Improved Techniques for Training GANscited by 2,970
  8. 2020Learning to summarize from human feedbackcited by 2,588
  9. 2021CLIPScore: A Reference-free Evaluation Metric for Image Captioningcited by 2,424
  10. 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,555
  11. 2023Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesiscited by 890
  12. 2020The State and Fate of Linguistic Diversity and Inclusion in the NLP Worldcited by 798
19 more
  1. 2024Evaluating Text-to-Visual Generation with Image-to-Text Generationcited by 474
  2. 2021Multimodal datasets: misogyny, pornography, and malignant stereotypescited by 327
  3. 2021Visually Grounded Reasoning across Languages and Culturescited by 189
  4. 2024BLEnD: A Benchmark for LLMs on Everyday Knowledge in Diverse Cultures and Languagescited by 173
  5. 2024Towards Measuring and Modeling "Culture" in LLMs: A Surveycited by 167
  6. 2024GenAI-Bench: Evaluating and Improving Compositional Text-to-Visual Generationcited by 135
  7. 2024CVQA: Culturally-diverse Multilingual Visual Question Answering Benchmarkcited by 120
  8. 2023SeeGULL: A Stereotype Benchmark with Broad Geo-Cultural Coverage Leveraging Generative Modelscited by 66
  9. 2024CULTURE-GEN: Revealing Global Cultural Perception in Language Models through Natural Language Promptingcited by 55
  10. 2025CultureVLM: Characterizing and Improving Cultural Understanding of Vision-Language Models for over 100 Countriescited by 42
  11. 2023Are Personalized Stochastic Parrots More Dangerous? Evaluating Persona Biases in Dialogue Systemscited by 37
  12. 2024An image speaks a thousand words, but can everyone listen? On image transcreation for cultural relevancecited by 36
  13. 2023Improving Contrastive Learning of Sentence Embeddings from AI Feedbackcited by 29
  14. 2024FoodieQA: A Multimodal Dataset for Fine-Grained Understanding of Chinese Food Culturecited by 25
  15. 2023Cultural Compass: Predicting Transfer Learning Success in Offensive Language Detection with Cultural Featurescited by 18
  16. 2024Quality-Weighted Vendi Scores And Their Application To Diverse Experimental Designcited by 17
  17. 2023Towards Equitable Representation in Text-to-Image Synthesis Models with the Cross-Cultural Understanding Benchmark (CCUB) Datasetcited by 12
  18. 2024Why AI Is WEIRD and Should Not Be This Way: Towards AI For Everyone, With Everyone, By Everyonecited by 10
  19. 2024CIC: A Framework for Culturally-Aware Image Captioningcited by 8

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 9; 2026: 5.

14 papers.

Sort:

By area:

  1. 2025CulturalFrames: Assessing Cultural Expectation Alignment in Text-to-Image Models and Evaluation Metricscited by 15
  2. 2025Culture in Action: Evaluating Text-to-Image Models through Social Activitiescited by 10
  3. 2025Crowdsource, Crawl, or Generate? Creating SEA-VL, a Multicultural Vision-Language Dataset for Southeast Asiacited by 9
  4. 2025CuRe: Cultural Gaps in the Long Tail of Text-to-Image Systemscited by 8
  5. 2025Hanfu-Bench: A Multimodal Benchmark on Cross-Temporal Cultural Understanding and Transcreationcited by 5
  6. 2025Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Modelscited by 4
  7. 2025Exposing Blindspots: Cultural Bias Evaluation in Generative Image Modelscited by 4
  8. 2025World in a Frame: Understanding Culture Mixing as a New Challenge for Vision-Language Modelscited by 3
  9. 2026CultureVidBench: Benchmarking Cultural Understanding in Text-to-Video Generationcited by 1
  10. 2026Prompt Revision as a Source of Cultural Bias in Text-to-Image Systemscited by 1
  11. 2025Image Embedding Sampling Method for Diverse Captioningcited by 0
  12. 2026CultureScore: Evaluating Cultural Faithfulness in Video Generation Modelscited by 0
2 more
  1. 2026ImageEval 2026: Culturally Grounded Arabic Multimodal Evaluationcited by 0
  2. 2026CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systemscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Deconstructing Bias: A Multifaceted Framework for Diagnosing Cultural and Compositional Inequities in Text-to-Image Generative Models
  2. 2023On the Cultural Gap in Text-to-Image Generation
  3. 2024From Pampas to Pixels: Fine-Tuning Diffusion Models for Ga'ucho Heritage
  4. 2024From Local Concepts to Universals: Evaluating the Multicultural Understanding of Vision-Language Models
  5. 2025Culture-TRIP: Culturally-Aware Text-to-Image Generation with Iterative Prompt Refinement
  6. 2024Crossroads of Continents: Automated Artifact Extraction for Cultural Adaptation with Large Multimodal Models
  7. 2025CAIRe: Cultural Attribution of Images by Retrieval-Augmented Evaluation
  8. 2026T2I-BiasBench: A Multi-Metric Framework for Auditing Demographic and Cultural Bias in Text-to-Image Models