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

ACL ARR 2025 July Submission521 Authors

Abstract: Public opinion surveys show cross-cultural differences in political opinions between socio-cultural 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 Western 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 in Western language contexts, political opinions transfer between languages, demonstrating the challenges in achieving explicit socio-linguistic, 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,French,German,Italian,Spanish

Previous URL: https://openreview.net/forum?id=HRLmEgLXmA

Reassignment Request Area Chair: Yes, I want a different area chair for our submission

Reassignment Request Reviewers: Yes, I want a different set of reviewers

Justification For Not Keeping Action Editor Or Reviewers: Existing reviewers did not engage at all in rebuttal or ignored many aspects of the rebuttal.

A1 Limitations Section: This paper has a limitations section.

A2 Potential Risks: Yes

A2 Elaboration: Ethics Statement

B Use Or Create Scientific Artifacts: Yes

B1 Cite Creators Of Artifacts: Yes

B1 Elaboration: 3.1, 4.1

B2 Discuss The License For Artifacts: Yes

B2 Elaboration: Ethics Statement

B3 Artifact Use Consistent With Intended Use: No

B3 Elaboration: openly available research data that was used as such

B4 Data Contains Personally Identifying Info Or Offensive Content: N/A

B5 Documentation Of Artifacts: Yes

B5 Elaboration: 3.1, 4.1, Appendix

B6 Statistics For Data: Yes

B6 Elaboration: 3.1,4.1,Appendix

C Computational Experiments: Yes

C1 Model Size And Budget: Yes

C1 Elaboration: 3.1,Appendix

C2 Experimental Setup And Hyperparameters: Yes

C2 Elaboration: Appendix

C3 Descriptive Statistics: Yes

C3 Elaboration: 3.2,4.2

C4 Parameters For Packages: N/A

D Human Subjects Including Annotators: Yes

D1 Instructions Given To Participants: Yes

D1 Elaboration: Appendix

D2 Recruitment And Payment: Yes

D2 Elaboration: Appendix

D3 Data Consent: Yes

D3 Elaboration: Appendix

D4 Ethics Review Board Approval: N/A

D5 Characteristics Of Annotators: Yes

D5 Elaboration: Appendix

E Ai Assistants In Research Or Writing: Yes

E1 Information About Use Of Ai Assistants: No

E1 Elaboration: ChatGPT for the coding, but not for writing the paper

Author Submission Checklist: yes

Submission Number: 521