mlsanityData to 7 Oct 2026

Culturally uneven urban perception in large language models

arXiv 2604.20048 ↗First posted 21 Apr 2026cs.CL cs.CYcited by 1

Not on the map. Why?

Abstract (arXiv)

Large language models (LLMs) are increasingly used to describe and evaluate cities, yet the cultural structure of their urban judgments remains understudied. Here we introduce a measurement framework for testing whether LLM-based urban perception is culturally neutral, using a globally stratified street-view image dataset. Open-ended descriptions and structured scores generated by three frontier multimodal models all show that the neutral baseline lies closer to regional framings associated with Europe and North America than to other cultural framings. Comparisons between AI and human urban perception further show that prompting can move AI responses closer to specific regional human descriptions, but fails to recover the variety and diversity of human responses, flattening observed demographic patterns and introducing sentiment-based self-favouring bias. These results indicate a systematic risk in treating AI as a neutral tool for urban tasks, especially when model outputs are used to compare, evaluate or represent cities across cultural contexts.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 20 of its 47 references that are in the map. First posted on arXiv 21 Apr 2026.

Builds on

20 of 47 references.

References · 20

  1. 2023Role-Play with Large Language Modelscited by 290
  2. 2024Towards Measuring and Modeling "Culture" in LLMs: A Surveycited by 166
  3. 2023Cultural Bias and Cultural Alignment of Large Language Modelscited by 149
  4. 2024Investigating Cultural Alignment of Large Language Modelscited by 140
  5. 2024Large language models that replace human participants can harmfully misportray and flatten identity groupscited by 137
  6. 2023Generative AIcited by 119
  7. 2024What Large Language Models Know and What People Think They Knowcited by 109
  8. 2023Generative Language Models Exhibit Social Identity Biasescited by 107
  9. 2024Large Language Models are Geographically Biasedcited by 91
  10. 2016Deep Learning the City : Quantifying Urban Perception At A Global Scalecited by 65
  11. 2024CultureLLM: Incorporating Cultural Differences into Large Language Modelscited by 49
  12. 2025UrbanLLaVA: A Multi-modal Large Language Model for Urban Intelligence with Spatial Reasoning and Understandingcited by 15
8 more
  1. 2025Global urban visual perception varies across demographics and personalitiescited by 10
  2. 2025Risks of Cultural Erasure in Large Language Modelscited by 9
  3. 2024Urban Safety Perception Assessments via Integrating Multimodal Large Language Models with Street View Imagescited by 7
  4. 2025Rethinking LLM Bias Probing Using Lessons from the Social Sciencescited by 6
  5. 2025Streetscape Analysis with Generative AI (SAGAI): Vision-Language Assessment and Mapping of Urban Scenescited by 6
  6. 2025Do Vision-Language Models See Urban Scenes as People Do? An Urban Perception Benchmarkcited by 4
  7. 2025Multimodal Large Language Models Predict Urban Safety Perception but Encode Non-Neutral Demographic Priorscited by 3
  8. 2026UrbanAlign: Post-hoc Semantic Calibration for VLM-Human Preference Alignmentcited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Mapping the City Through the Lens of Language Modelscited by 0