Metraipolis › archive › dc_f895a4e81ed6

Representational Equality in Cross-country Value Simulation: A Systematic Analysis of Large Language Models — arXiv:2608.08058

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.08058
License (as archived)
CC0-1.0
Archived
2026-10-19T08:54:56.232Z
SHA-256 of the archived text
8053402fe08bc9ce7d1f6a64310716a1413be0792ab1d45d8034630699c2595d
Stable URL of this page
https://metraipolis.com/documento/dc_f895a4e81ed6

How to cite

Representational Equality in Cross-country Value Simulation: A Systematic Analysis of Large Language Models — arXiv:2608.08058 — arXiv (en), https://arxiv.org/abs/2608.08058 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f895a4e81ed6 (Metraipolis archive dc_f895a4e81ed6, sha256 8053402fe08bc9ce7d1f6a64310716a1413be0792ab1d45d8034630699c2595d)
BibTeX
@misc{dcf895a4e81ed6,
  title = {Representational Equality in Cross-country Value Simulation: A Systematic Analysis of Large Language Models — arXiv:2608.08058},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.08058},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f895a4e81ed6; sha256 8053402fe08bc9ce7d1f6a64310716a1413be0792ab1d45d8034630699c2595d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.08058. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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.

Tema degli esploratori: governance digitale e beni comuni (retro-catalogo arXiv: annunci del 2026-08-11 in cs.CY).
Categorie arXiv: Computers and Society (cs.CY).
Pagina del lavoro: https://arxiv.org/abs/2608.08058 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T08:51:53.740Z dalla pagina https://arxiv.org/catchup/cs.CY/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).