Representational Equality in Cross-country Value Simulation: A Systematic Analysis of Large Language Models
Computational Linguistics · 11.11.2026 · 1-57
DOI: 10.1162/coli.a.648 ↗Kurz gefasst
Fachartikel in der Zeitschrift Computational Linguistics, online erschienen am 11.11.2026. Verfasst von Xiaowen Jian und 5 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).
Abstract (Originalsprache)
Traditional methods for studying human opinions often struggle to support representative and scalable research across countries. Large language models (LLMs) can serve as scalable proxies for simulating human opinions, enabling more efficient opinion analysis. However, this use of LLMs requires not only high average accuracy but also representational equality, that is, comparable simulation accuracy across populations. Uneven simulation accuracy may reproduce or amplify societal biases in downstream applications. This study systematically investigates country-level representational equality across 59 countries and finds substantial, systematic inequality. Populations from wealthier and more technologically advanced countries are simulated more accurately. We further compare two foundational intervention pathways, contextual adaptation and parametric modification, and show that improvements in average or target-group accuracy do not necessarily translate into greater representational equality. For contextual adaptation, native-language prompting generally improves accuracy but remains model-dependent, whereas additional information more often improves both accuracy and equality. For parametric modification, language-specific continued post-training improves accuracy for targeted language groups but unevenly, while preference alignment yields no systematic gains in accuracy or equality. Human-annotated preference data generally preserve accuracy better than AI-annotated data. These findings highlight the need for representational equality alongside accuracy and offer guidance for more inclusive, socially responsible LLM-based simulations.
Zitieren
APA
Jian, X., Mou, X., Gong, D., Qian, C., Chen, H., & Sun, M. (2026). Representational Equality in Cross-country Value Simulation: A Systematic Analysis of Large Language Models. Computational Linguistics, 1-57. https://doi.org/10.1162/coli.a.648
Vancouver
Jian X, Mou X, Gong D, Qian C, Chen H, Sun M. Representational Equality in Cross-country Value Simulation: A Systematic Analysis of Large Language Models. Computational Linguistics. 2026:1-57. doi:10.1162/coli.a.648
BibTeX
@article{Jian2026,
author = {Jian, Xiaowen and Mou, Xinyi and Gong, Daisong and Qian, Chen and Chen, Huimin and Sun, Maosong},
title = {Representational Equality in Cross-country Value Simulation: A Systematic Analysis of Large Language Models},
journal = {Computational Linguistics},
year = {2026},
pages = {1--57},
doi = {10.1162/coli.a.648}
}
EUVIMED