Multilingual Political Views of Large Language Models: Identification and Steering
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912678907215872 |
|---|---|
| author | Gurgurov, Daniil Trinley, Katharina Vykopal, Ivan van Genabith, Josef Ostermann, Simon Zamparelli, Roberto |
| author_facet | Gurgurov, Daniil Trinley, Katharina Vykopal, Ivan van Genabith, Josef Ostermann, Simon Zamparelli, Roberto |
| contents | 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. Our code is publicly available at https://github.com/d-gurgurov/Political-Ideologies-LLMs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_22623 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Multilingual Political Views of Large Language Models: Identification and Steering Gurgurov, Daniil Trinley, Katharina Vykopal, Ivan van Genabith, Josef Ostermann, Simon Zamparelli, Roberto Computation and Language 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. Our code is publicly available at https://github.com/d-gurgurov/Political-Ideologies-LLMs. |
| title | Multilingual Political Views of Large Language Models: Identification and Steering |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2507.22623 |