Multilingual Political Views of Large Language Models: Identification and Steering

ACL ARR 2025 July Submission611 Authors

Abstract:

Large language models (LLMs) are increasingly used in everyday tools and applications, raising concerns about their potential influence on political views. While prior research has shown that LLMs often exhibit measurable political biases--frequently skewing toward liberal or progressive positions--key gaps remain. Most existing studies evaluate only a narrow set of models and languages, leaving open questions about the generalizability of political biases across architectures, scales, and multilingual settings. Moreover, few works examine whether these biases can be actively controlled.

In this work, we address these gaps through a large-scale study of political orientation in modern open-source instruction-tuned LLMs. We evaluate seven models, including LLaMA-3.1, Qwen-3, and Aya-Expanse, across 14 languages using the Political Compass Test with 11 semantically equivalent paraphrases per statement to ensure robust measurement. Our results reveal that larger models consistently shift toward libertarian-left positions, with significant variations across languages and model families. To test the manipulability of political stances, we utilize a simple center-of-mass activation intervention technique and show that it reliably steers model responses toward alternative ideological positions across multiple languages.

Paper Type: Long

Research Area: Ethics, Bias, and Fairness

Research Area Keywords: model bias/fairness evaluation, model bias/unfairness mitigation

Contribution Types: Model analysis & interpretability

Languages Studied: Bulgarian, Czech, German, English, Spanish, French, Italian, Persian, Polish, Portuguese-Portugal, Romanian, Russian, Slovenian, Turkish

Reassignment Request Area Chair: This is not a resubmission

Reassignment Request Reviewers: This is not a resubmission

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: Section 3 and 4

B2 Discuss The License For Artifacts: N/A

B3 Artifact Use Consistent With Intended Use: Yes

B3 Elaboration: Section 3

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

B5 Documentation Of Artifacts: Yes

B5 Elaboration: Section 3

B6 Statistics For Data: N/A

C Computational Experiments: Yes

C1 Model Size And Budget: Yes

C1 Elaboration: Section 3 - we provide the details on the model sizes; the other details are not applicable since we only perform inference analysis

C2 Experimental Setup And Hyperparameters: N/A

C3 Descriptive Statistics: Yes

C3 Elaboration: Section 4 and Appendix

C4 Parameters For Packages: Yes

C4 Elaboration: Appendix A - generation parameters

D Human Subjects Including Annotators: No

D1 Instructions Given To Participants: N/A

D2 Recruitment And Payment: N/A

D3 Data Consent: N/A

D4 Ethics Review Board Approval: N/A

D5 Characteristics Of Annotators: N/A

E Ai Assistants In Research Or Writing: No

E1 Information About Use Of Ai Assistants: N/A

Author Submission Checklist: yes

Submission Number: 611