# CulturalFrames: Assessing Cultural Expectation Alignment in Text-to-Image Models and Evaluation Metrics

arXiv: https://arxiv.org/abs/2506.08835 · HTML: https://mlsanity.com/paper/2506.08835/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 63 references that are in the map.
- First posted on arXiv 10 Jun 2025.

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

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Evaluating Text-to-Visual Generation with Image-to-Text Generation](https://mlsanity.com/paper/2404.01291/) (2024)
- [TIFA: Accurate and Interpretable Text-to-Image Faithfulness Evaluation with Question Answering](https://mlsanity.com/paper/2303.11897/) (2023)
- [The Vendi Score: A Diversity Evaluation Metric for Machine Learning](https://mlsanity.com/paper/2210.02410/) (2022)
- [Human Preference Score: Better Aligning Text-to-Image Models with Human Preference](https://mlsanity.com/paper/2303.14420/) (2023)
- [DALL-Eval: Probing the Reasoning Skills and Social Biases of Text-to-Image Generation Models](https://mlsanity.com/paper/2202.04053/) (2022)
- [Challenges and Strategies in Cross-Cultural NLP](https://mlsanity.com/paper/2203.10020/) (2022)
- [Davidsonian Scene Graph: Improving Reliability in Fine-grained Evaluation for Text-to-Image Generation](https://mlsanity.com/paper/2310.18235/) (2023)
- [Towards Measuring and Modeling "Culture" in LLMs: A Survey](https://mlsanity.com/paper/2403.15412/) (2024)
- [Teaching Large Language Models to Regress Accurate Image Quality Scores using Score Distribution](https://mlsanity.com/paper/2501.11561/) (2025)
- [Social Biases through the Text-to-Image Generation Lens](https://mlsanity.com/paper/2304.06034/) (2023)
- [What You See is What You Read? Improving Text-Image Alignment Evaluation](https://mlsanity.com/paper/2305.10400/) (2023)
- [LLMScore: Unveiling the Power of Large Language Models in Text-to-Image Synthesis Evaluation](https://mlsanity.com/paper/2305.11116/) (2023)
- [VL-RewardBench: A Challenging Benchmark for Vision-Language Generative Reward Models](https://mlsanity.com/paper/2411.17451/) (2024)
- [GenAI Arena: An Open Evaluation Platform for Generative Models](https://mlsanity.com/paper/2406.04485/) (2024)
- [StoryDALL-E: Adapting Pretrained Text-to-Image Transformers for Story Continuation](https://mlsanity.com/paper/2209.06192/) (2022)
- [Survey of Bias In Text-to-Image Generation: Definition, Evaluation, and Mitigation](https://mlsanity.com/paper/2404.01030/) (2024)
- [An image speaks a thousand words, but can everyone listen? On image transcreation for cultural relevance](https://mlsanity.com/paper/2404.01247/) (2024)
- [Exploiting Cultural Biases via Homoglyphs in Text-to-Image Synthesis](https://mlsanity.com/paper/2209.08891/) (2022)
- [ViSAGe: A Global-Scale Analysis of Visual Stereotypes in Text-to-Image Generation](https://mlsanity.com/paper/2401.06310/) (2024)
- [SCoFT: Self-Contrastive Fine-Tuning for Equitable Image Generation](https://mlsanity.com/paper/2401.08053/) (2024)
- [Diffusion Models Through a Global Lens: Are They Culturally Inclusive?](https://mlsanity.com/paper/2502.08914/) (2025)
- [LIVS: A Pluralistic Alignment Dataset for Inclusive Public Spaces](https://mlsanity.com/paper/2503.01894/) (2025)
- [Insights on Disagreement Patterns in Multimodal Safety Perception across Diverse Rater Groups](https://mlsanity.com/paper/2410.17032/) (2024)

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

- [Qwen-Image-Bench: From Generation to Creation in Text-to-Image Evaluation](https://mlsanity.com/paper/2605.28091/) (2026)
- [Whose View of Safety? A Deep DIVE Dataset for Pluralistic Alignment of Text-to-Image Models](https://mlsanity.com/paper/2507.13383/) (2025)
- [Culture in Action: Evaluating Text-to-Image Models through Social Activities](https://mlsanity.com/paper/2511.05681/) (2025)
- [Computational Hermeneutics: Evaluating generative AI as a cultural technology](https://mlsanity.com/paper/2604.16403/) (2026)
- [Tears or Cheers? Benchmarking LLMs via Culturally Elicited Distinct Affective Responses](https://mlsanity.com/paper/2601.13024/) (2026)
- [Person-Centric Annotations of LAION-400M: Auditing Bias and Its Transfer to Models](https://mlsanity.com/paper/2510.03721/) (2025)
- [Exposing Blindspots: Cultural Bias Evaluation in Generative Image Models](https://mlsanity.com/paper/2510.20042/) (2025)
- [When Cultures Move: Measuring and Improving Multicultural Text-to-Video Generation](https://mlsanity.com/paper/2605.16716/) (2026)
- [Debiasing Text-to-Image Evaluation via Implicit Cultural Alignment Reward Modeling](https://mlsanity.com/paper/2607.15740/) (2026)
- [Prompt Revision as a Source of Cultural Bias in Text-to-Image Systems](https://mlsanity.com/paper/2609.11532/) (2026)
- [CultureScore: Evaluating Cultural Faithfulness in Video Generation Models](https://mlsanity.com/paper/2606.07311/) (2026)
- [Toward Cultural Alignment: Human-Centered Evaluation of Multimodal AI Stories Across Five African Communities](https://mlsanity.com/paper/2608.29209/) (2026)
- [ImageEval 2026: Culturally Grounded Arabic Multimodal Evaluation](https://mlsanity.com/paper/2608.30475/) (2026)
- [CultureMINE: Datasets and Methods for Improving the Cultural Capabilities of NLP Systems](https://mlsanity.com/paper/2609.22494/) (2026)
- [VisExMEM: Visual Evidence-Based Explainable Multimodal Evaluation Metric](https://mlsanity.com/paper/2610.16441/) (2026)

## Abstract (arXiv)

The increasing ubiquity of text-to-image (T2I) models as tools for visual content generation raises concerns about their ability to accurately represent diverse cultural contexts -- where missed cues can stereotype communities and undermine usability. In this work, we present the first study to systematically quantify the alignment of T2I models and evaluation metrics with respect to both explicit (stated) as well as implicit (unstated, implied by the prompt's cultural context) cultural expectations. To this end, we introduce CulturalFrames, a novel benchmark designed for rigorous human evaluation of cultural representation in visual generations. Spanning 10 countries and 5 socio-cultural domains, CulturalFrames comprises 983 prompts, 3637 corresponding images generated by 4 state-of-the-art T2I models, and over 10k detailed human annotations. We find that across models and countries, cultural expectations are missed an average of 44% of the time. Among these failures, explicit expectations are missed at a surprisingly high average rate of 68%, while implicit expectation failures are also significant, averaging 49%. Furthermore, we show that existing T2I evaluation metrics correlate poorly with human judgments of cultural alignment, irrespective of their internal reasoning. Collectively, our findings expose critical gaps, provide a concrete testbed, and outline actionable directions for developing culturally informed T2I models and metrics that improve global usability.