# Culturally uneven urban perception in large language models

arXiv: https://arxiv.org/abs/2604.20048 · HTML: https://mlsanity.com/paper/2604.20048/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 47 references that are in the map.
- First posted on arXiv 21 Apr 2026.

## Builds on (most cited first, 20 of 20)

- [Role-Play with Large Language Models](https://mlsanity.com/paper/2305.16367/) (2023)
- [Towards Measuring and Modeling "Culture" in LLMs: A Survey](https://mlsanity.com/paper/2403.15412/) (2024)
- [Cultural Bias and Cultural Alignment of Large Language Models](https://mlsanity.com/paper/2311.14096/) (2023)
- [Large language models that replace human participants can harmfully misportray and flatten identity groups](https://mlsanity.com/paper/2402.01908/) (2024)
- [Investigating Cultural Alignment of Large Language Models](https://mlsanity.com/paper/2402.13231/) (2024)
- [Generative AI](https://mlsanity.com/paper/2309.07930/) (2023)
- [Generative Language Models Exhibit Social Identity Biases](https://mlsanity.com/paper/2310.15819/) (2023)
- [What Large Language Models Know and What People Think They Know](https://mlsanity.com/paper/2401.13835/) (2024)
- [Large Language Models are Geographically Biased](https://mlsanity.com/paper/2402.02680/) (2024)
- [Deep Learning the City : Quantifying Urban Perception At A Global Scale](https://mlsanity.com/paper/1608.01769/) (2016)
- [CultureLLM: Incorporating Cultural Differences into Large Language Models](https://mlsanity.com/paper/2402.10946/) (2024)
- [UrbanLLaVA: A Multi-modal Large Language Model for Urban Intelligence with Spatial Reasoning and Understanding](https://mlsanity.com/paper/2506.23219/) (2025)
- [Global urban visual perception varies across demographics and personalities](https://mlsanity.com/paper/2505.12758/) (2025)
- [Risks of Cultural Erasure in Large Language Models](https://mlsanity.com/paper/2501.01056/) (2025)
- [Urban Safety Perception Assessments via Integrating Multimodal Large Language Models with Street View Images](https://mlsanity.com/paper/2407.19719/) (2024)
- [Rethinking LLM Bias Probing Using Lessons from the Social Sciences](https://mlsanity.com/paper/2503.00093/) (2025)
- [Streetscape Analysis with Generative AI (SAGAI): Vision-Language Assessment and Mapping of Urban Scenes](https://mlsanity.com/paper/2504.16538/) (2025)
- [Do Vision-Language Models See Urban Scenes as People Do? An Urban Perception Benchmark](https://mlsanity.com/paper/2509.14574/) (2025)
- [Multimodal Large Language Models Predict Urban Safety Perception but Encode Non-Neutral Demographic Priors](https://mlsanity.com/paper/2503.00610/) (2025)
- [UrbanAlign: Post-hoc Semantic Calibration for VLM-Human Preference Alignment](https://mlsanity.com/paper/2602.19442/) (2026)

## Built on by (most cited first, 1 of 1)

- [Mapping the City Through the Lens of Language Models](https://mlsanity.com/paper/2608.02971/) (2026)

## 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.