# Where Culture Fades: Revealing the Cultural Gap in Text-to-Image Generation

arXiv: https://arxiv.org/abs/2511.17282 · HTML: https://mlsanity.com/paper/2511.17282/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 42 of its 52 references that are in the map.
- First posted on arXiv 21 Nov 2025.

## Builds on (most cited first, 30 of 42)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding](https://mlsanity.com/paper/2205.11487/) (2022)
- [SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis](https://mlsanity.com/paper/2307.01952/) (2023)
- [Scaling Rectified Flow Transformers for High-Resolution Image Synthesis](https://mlsanity.com/paper/2403.03206/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation](https://mlsanity.com/paper/2208.12242/) (2022)
- [CLIPScore: A Reference-free Evaluation Metric for Image Captioning](https://mlsanity.com/paper/2104.08718/) (2021)
- [Sparse Autoencoders Find Highly Interpretable Features in Language Models](https://mlsanity.com/paper/2309.08600/) (2023)
- [Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation](https://mlsanity.com/paper/2211.12572/) (2022)
- [InstantBooth: Personalized Text-to-Image Generation without Test-Time Finetuning](https://mlsanity.com/paper/2304.03411/) (2023)
- [Ablating Concepts in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.13516/) (2023)
- [Show-o2: Improved Native Unified Multimodal Models](https://mlsanity.com/paper/2506.15564/) (2025)
- [Stable Bias: Analyzing Societal Representations in Diffusion Models](https://mlsanity.com/paper/2303.11408/) (2023)
- [Compositional Explanations of Neurons](https://mlsanity.com/paper/2006.14032/) (2020)
- [Fair Diffusion: Instructing Text-to-Image Generation Models on Fairness](https://mlsanity.com/paper/2302.10893/) (2023)
- [Editing Implicit Assumptions in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.08084/) (2023)
- [Language-Specific Neurons: The Key to Multilingual Capabilities in Large Language Models](https://mlsanity.com/paper/2402.16438/) (2024)
- [AnomalyDiffusion: Few-Shot Anomaly Image Generation with Diffusion Model](https://mlsanity.com/paper/2312.05767/) (2023)
- [SeaEval for Multilingual Foundation Models: From Cross-Lingual Alignment to Cultural Reasoning](https://mlsanity.com/paper/2309.04766/) (2023)
- [The Bias Amplification Paradox in Text-to-Image Generation](https://mlsanity.com/paper/2308.00755/) (2023)
- [OpenBias: Open-set Bias Detection in Text-to-Image Generative Models](https://mlsanity.com/paper/2404.07990/) (2024)
- [Multimodal Neurons in Pretrained Text-Only Transformers](https://mlsanity.com/paper/2308.01544/) (2023)
- [Finding and Editing Multi-Modal Neurons in Pre-Trained Transformers](https://mlsanity.com/paper/2311.07470/) (2023)
- [Interpreting Arithmetic Mechanism in Large Language Models through Comparative Neuron Analysis](https://mlsanity.com/paper/2409.14144/) (2024)
- [AltDiffusion: A Multilingual Text-to-Image Diffusion Model](https://mlsanity.com/paper/2308.09991/) (2023)
- [CosmicMan: A Text-to-Image Foundation Model for Humans](https://mlsanity.com/paper/2404.01294/) (2024)
- [SSMG: Spatial-Semantic Map Guided Diffusion Model for Free-form Layout-to-Image Generation](https://mlsanity.com/paper/2308.10156/) (2023)
- [ViSAGe: A Global-Scale Analysis of Visual Stereotypes in Text-to-Image Generation](https://mlsanity.com/paper/2401.06310/) (2024)

## Built on by (most cited first, 11 of 11)

- [DNA: Uncovering Universal Latent Forgery Knowledge](https://mlsanity.com/paper/2601.22515/) (2026)
- [Bias Is a Subspace, Not a Coordinate: A Geometric Rethinking of Post-hoc Debiasing in Vision-Language Models](https://mlsanity.com/paper/2511.18123/) (2025)
- [OrthoEraser: Coupled-Neuron Orthogonal Projection for Concept Erasure](https://mlsanity.com/paper/2603.11493/) (2026)
- [Latent Anomaly Knowledge Excavation: Unveiling Sparse Sensitive Neurons in Vision-Language Models](https://mlsanity.com/paper/2604.07802/) (2026)
- [PhenoYieldNet: Learning Crop-Aware Phenological Responses for Multi-Crop Yield Prediction](https://mlsanity.com/paper/2605.23478/) (2026)
- [Q-BridgeNet: A Quantization Network for Cross-Lingual Sign Language Translation](https://mlsanity.com/paper/2607.11215/) (2026)
- [No Single Neuron of Failure: Distributed Safety Alignment Against White-Box Attacks](https://mlsanity.com/paper/2608.01414/) (2026)
- [Moving the Safety Barrier: Dynamic Routing Adaptive Alignment Against White-Box Attacks](https://mlsanity.com/paper/2608.02674/) (2026)
- [BARQ: Balanced Codebook Refinement for Low-Bit LLM Quantization](https://mlsanity.com/paper/2610.04490/) (2026)
- [Do correct answers have stable latent knowledge support?](https://mlsanity.com/paper/2610.15277/) (2026)
- [SuperAI: Merging Capabilities Across Heterogeneous Foundation Models](https://mlsanity.com/paper/2610.15322/) (2026)

## Abstract (arXiv)

Multilingual text-to-image (T2I) models have advanced rapidly in terms of visual realism and semantic alignment, and are now widely utilized. Yet outputs vary across cultural contexts: because language carries cultural connotations, images synthesized from multilingual prompts should preserve cross-lingual cultural consistency. We conduct a comprehensive analysis showing that current T2I models often produce culturally neutral or English-biased results under multilingual prompts. Analyses of two representative models indicate that the issue stems not from missing cultural knowledge but from insufficient activation of culture-related representations. We propose a probing method that localizes culture-sensitive signals to a small set of neurons in a few fixed layers. Guided by this finding, we introduce two complementary alignment strategies: (1) inference-time cultural activation that amplifies the identified neurons without backbone fine-tuned; and (2) layer-targeted cultural enhancement that updates only culturally relevant layers. Experiments on our CultureBench demonstrate consistent improvements over strong baselines in cultural consistency while preserving fidelity and diversity.