Mirroring Cultural Dominance: Disclosing Large Language Models Social Values, Attitudes and Stereotypes
Societies · 21.05.2025 · 15 (5) · 142
DOI: 10.3390/soc15050142 ↗Kurz gefasst
Fachartikel in der Zeitschrift Societies, online erschienen am 21.05.2025. Verfasst von Kristian Dokic und 2 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref) und nennt 79 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University of Osijek, Faculty of Tourism and Rural Development.
Abstract (Originalsprache)
The paper aims to address large language models’ (LLMs) cultural bias using the World Value Survey Wave 7 (WVS) questionnaire on social values, attitudes, and stereotypes. Comparative analysis and LLMs interview methods measure the Euclidean distance of response vectors of four culturally diverse LLMs (USA, China, Russia, UAE) in a multidimensional vector space to contrast originated WVS research countries and population positions. The results confirmed the initial hypotheses reflecting culturally and linguistically biased LLM answers, considering specific socio-cultural contexts and English language and Latin script digital dominance in available training materials. USA-constructed LLMs showed the most liberal attitudes, followed by China, Russia, and the UAE. LLM interview results also show WVS results closest to the United States population, positioning the similarity of the responses in first place for China and Russia followed by the USA and the UAE. Mitigating initiatives in LLMs’ cultural and linguistic debiasing is required to preserve cultural and linguistic diversity in the digital space.
Förderung
- University of Osijek, Faculty of Tourism and Rural Development
Zitieren
APA
Dokic, K., Pisker, B., & Radisic, B. (2025). Mirroring Cultural Dominance: Disclosing Large Language Models Social Values, Attitudes and Stereotypes. Societies, 15(5), 142. https://doi.org/10.3390/soc15050142
Vancouver
Dokic K, Pisker B, Radisic B. Mirroring Cultural Dominance: Disclosing Large Language Models Social Values, Attitudes and Stereotypes. Societies. 2025;15(5):142. doi:10.3390/soc15050142
BibTeX
@article{Dokic2025,
author = {Dokic, Kristian and Pisker, Barbara and Radisic, Bojan},
title = {Mirroring Cultural Dominance: Disclosing Large Language Models Social Values, Attitudes and Stereotypes},
journal = {Societies},
year = {2025},
volume = {15},
number = {5},
pages = {142},
doi = {10.3390/soc15050142}
}
EUVIMED