Multilingual Political Views of Large Language Models: Identification and Steering

TL;DR

This study investigates political biases in open-source multilingual LLMs, revealing a tendency toward libertarian-left views in larger models and demonstrating a method to steer these biases across various languages.

Contribution

It provides a large-scale, multilingual analysis of political biases in instruction-tuned LLMs and introduces a simple intervention technique to actively steer model responses.

Findings

Larger models tend to lean libertarian-left.

Political biases vary across languages and model types.

A simple intervention can reliably steer model responses.

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. Our code is publicly available at https://github.com/d-gurgurov/Political-Ideologies-LLMs.