Large language models create an uneven informational layer over cities

2026-07-07

AI Summary

This study addresses a dual bias in large language models (LLMs) for urban venue recommendation: the systematic omission of real establishments alongside the generation of fictitious ones, potentially exacerbating economic inequality. By auditing restaurant recommendations from three leading LLMs across 304 neighborhoods in five U.S. cities using 320 synthetic user profiles spanning income, age, gender, and residency status, the research reveals— for the first time—that this bias stems from shared visibility patterns rather than model-specific errors. Findings show that user identity significantly shapes recommendations: 47.5% of actual restaurants were never suggested, with 31.9% of these omissions consistent across all models. Higher-income users and tourists received more expensive and diverse options. Simulations indicate that reliance on LLMs would shift consumer spending from chain fast food toward independent full-service restaurants.

Abstract

Large language models (LLMs) are emerging as a new informational layer over cities, shaping which places people discover, consider, and ultimately visit. Yet little is known about which places they surface, which they ignore, and whether these patterns vary across communities and users and translate into real-world economic consequences. Here, we audit restaurant recommendations from three major LLMs across 304 neighborhoods in five U.S. cities using 320 synthetic user profiles spanning income, age, sex, and residential status. We find that LLMs both fabricate venues and systematically overlook real ones. Fabrication is concentrated in neighborhoods with weaker digital and physical footprints and disappears when models are provided with verified venue lists. In contrast, invisibility persists: even when choosing from a fixed set of real venues, 47.5% of establishments are never recommended, and 31.9% of these blind spots are shared across all three model families, indicating that uneven visibility reflects not only missing knowledge but also stable patterns of selective attention rooted in shared patterns of visibility rather than model-specific errors. The same selectivity extends to users. Within identical venue pools, higher-income users receive more expensive and less popular venues, while tourists are directed toward costlier but more socially diverse establishments than local residents. Simulating the resulting shifts in consumer demand suggests that widespread reliance on LLM recommendations would redirect visits and revenue away from chain and quick-service restaurants toward independent and full-service dining. Together, our findings show that LLMs act as a selective layer of urban information that unevenly distributes visibility across places and people, with potential consequences for local economies and urban inequality.

Problem

• large language models
• urban information
• recommendation bias
• digital inequality
• economic impact

Innovation

• large language models
• algorithmic bias
• urban informatics
• recommendation systems
• digital inequality