Do Political Opinions Transfer Between Languages? An Analysis of Unaligned and Aligned Multilingual LLMs

ACL ARR 2025 May Submission1215 Authors

Abstract: Public opinion surveys show cross-cultural differences in political opinions between sociocultural contexts. However, there is no clear evidence whether these differences translate to cross-lingual differences in multilingual large language models (MLLMs). We analyze whether opinions transfer between languages or whether there are separate opinions for each language in MLLMs of various sizes across five languages. We evaluate MLLMs' opinions by prompting them to report their (dis)agreement with political statements from voting advice applications. To better understand the interaction between languages in the models, we evaluate them both before and after aligning them with more left or right views using direct preference optimization and English alignment data only. Our findings reveal that unaligned models show only very few significant cross-lingual differences in the political opinions they reflect. The political alignment shifts opinions almost uniformly across all five languages. We conclude that political opinions transfer between languages, demonstrating the challenges in achieving explicit sociolinguistic, cultural, and political alignment of MLLMs.

Paper Type: Long

Research Area: Computational Social Science and Cultural Analytics

Research Area Keywords: political bias,cross-lingual transfer,multilingual evaluation,stance detection,sociolinguistics

Contribution Types: Model analysis & interpretability

Languages Studied: English, German, Italian, French, Spanish

Submission Number: 1215