Enregistré dans:
Détails bibliographiques
Auteurs principaux: Zhang, Jinghao, Jiang, Sihang, Guo, Shiwei, Chen, Shisong, Xiao, Yanghua, Feng, Hongwei, Liang, Jiaqing, HE, Minggui, Tao, Shimin, Ma, Hongxia
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2509.16188
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866915503344189440
author Zhang, Jinghao
Jiang, Sihang
Guo, Shiwei
Chen, Shisong
Xiao, Yanghua
Feng, Hongwei
Liang, Jiaqing
HE, Minggui
Tao, Shimin
Ma, Hongxia
author_facet Zhang, Jinghao
Jiang, Sihang
Guo, Shiwei
Chen, Shisong
Xiao, Yanghua
Feng, Hongwei
Liang, Jiaqing
HE, Minggui
Tao, Shimin
Ma, Hongxia
contents As large language models (LLMs) are increasingly deployed in diverse cultural environments, evaluating their cultural understanding capability has become essential for ensuring trustworthy and culturally aligned applications. However, most existing benchmarks lack comprehensiveness and are challenging to scale and adapt across different cultural contexts, because their frameworks often lack guidance from well-established cultural theories and tend to rely on expert-driven manual annotations. To address these issues, we propose CultureScope, the most comprehensive evaluation framework to date for assessing cultural understanding in LLMs. Inspired by the cultural iceberg theory, we design a novel dimensional schema for cultural knowledge classification, comprising 3 layers and 140 dimensions, which guides the automated construction of culture-specific knowledge bases and corresponding evaluation datasets for any given languages and cultures. Experimental results demonstrate that our method can effectively evaluate cultural understanding. They also reveal that existing large language models lack comprehensive cultural competence, and merely incorporating multilingual data does not necessarily enhance cultural understanding. All code and data files are available at https://github.com/HoganZinger/Culture
format Preprint
id arxiv_https___arxiv_org_abs_2509_16188
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CultureScope: A Dimensional Lens for Probing Cultural Understanding in LLMs
Zhang, Jinghao
Jiang, Sihang
Guo, Shiwei
Chen, Shisong
Xiao, Yanghua
Feng, Hongwei
Liang, Jiaqing
HE, Minggui
Tao, Shimin
Ma, Hongxia
Computation and Language
Artificial Intelligence
As large language models (LLMs) are increasingly deployed in diverse cultural environments, evaluating their cultural understanding capability has become essential for ensuring trustworthy and culturally aligned applications. However, most existing benchmarks lack comprehensiveness and are challenging to scale and adapt across different cultural contexts, because their frameworks often lack guidance from well-established cultural theories and tend to rely on expert-driven manual annotations. To address these issues, we propose CultureScope, the most comprehensive evaluation framework to date for assessing cultural understanding in LLMs. Inspired by the cultural iceberg theory, we design a novel dimensional schema for cultural knowledge classification, comprising 3 layers and 140 dimensions, which guides the automated construction of culture-specific knowledge bases and corresponding evaluation datasets for any given languages and cultures. Experimental results demonstrate that our method can effectively evaluate cultural understanding. They also reveal that existing large language models lack comprehensive cultural competence, and merely incorporating multilingual data does not necessarily enhance cultural understanding. All code and data files are available at https://github.com/HoganZinger/Culture
title CultureScope: A Dimensional Lens for Probing Cultural Understanding in LLMs
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2509.16188