What can LLM tell us about cities?

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Li, Zhuoheng, Wang, Yaochen, Song, Zhixue, Huang, Yuqi, Bao, Rui, Zheng, Guanjie, Li, Zhenhui Jessie
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866929605595627520
author Li, Zhuoheng
Wang, Yaochen
Song, Zhixue
Huang, Yuqi
Bao, Rui
Zheng, Guanjie
Li, Zhenhui Jessie
author_facet Li, Zhuoheng
Wang, Yaochen
Song, Zhixue
Huang, Yuqi
Bao, Rui
Zheng, Guanjie
Li, Zhenhui Jessie
contents This study explores the capabilities of large language models (LLMs) in providing knowledge about cities and regions on a global scale. We employ two methods: directly querying the LLM for target variable values and extracting explicit and implicit features from the LLM correlated with the target variable. Our experiments reveal that LLMs embed a broad but varying degree of knowledge across global cities, with ML models trained on LLM-derived features consistently leading to improved predictive accuracy. Additionally, we observe that LLMs demonstrate a certain level of knowledge across global cities on all continents, but it is evident when they lack knowledge, as they tend to generate generic or random outputs for unfamiliar tasks. These findings suggest that LLMs can offer new opportunities for data-driven decision-making in the study of cities.
format Preprint
id arxiv_https___arxiv_org_abs_2411_16791
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle What can LLM tell us about cities?
Li, Zhuoheng
Wang, Yaochen
Song, Zhixue
Huang, Yuqi
Bao, Rui
Zheng, Guanjie
Li, Zhenhui Jessie
Computation and Language
Artificial Intelligence
Information Retrieval
This study explores the capabilities of large language models (LLMs) in providing knowledge about cities and regions on a global scale. We employ two methods: directly querying the LLM for target variable values and extracting explicit and implicit features from the LLM correlated with the target variable. Our experiments reveal that LLMs embed a broad but varying degree of knowledge across global cities, with ML models trained on LLM-derived features consistently leading to improved predictive accuracy. Additionally, we observe that LLMs demonstrate a certain level of knowledge across global cities on all continents, but it is evident when they lack knowledge, as they tend to generate generic or random outputs for unfamiliar tasks. These findings suggest that LLMs can offer new opportunities for data-driven decision-making in the study of cities.
title What can LLM tell us about cities?
topic Computation and Language
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2411.16791