The Language You Ask In: Language-Conditioned Ideological Divergence in LLM Analysis of Contested Political Documents

TL;DR

This study reveals that large language models produce significantly different ideological analyses depending on the language of the prompt, even when analyzing the same content, highlighting biases in multilingual AI applications.

Contribution

It demonstrates that prompt language influences ideological bias in LLM outputs, affecting cross-lingual analysis and AI deployment in polarized contexts.

Findings

Russian prompts yield pro-state narratives.

Ukrainian prompts produce Western liberal perspectives.

Systematic ideological divergence based on language.

Abstract

Large language models (LLMs) are increasingly deployed as analytical tools across multilingual contexts, yet their outputs may carry systematic biases conditioned by the language of the prompt. This study presents an experimental comparison of LLM-generated political analyses of a Ukrainian civil society document, using semantically equivalent prompts in Russian and Ukrainian. Despite identical source material and parallel query structures, the resulting analyses varied substantially in rhetorical positioning, ideological orientation, and interpretive conclusions. The Russian-language output echoed narratives common in Russian state discourse, characterizing civil society actors as illegitimate elites undermining democratic mandates. The Ukrainian-language output adopted vocabulary characteristic of Western liberal-democratic political science, treating the same actors as legitimate stakeholders within democratic contestation. These findings demonstrate that prompt language alone can produce systematically different ideological orientations from identical models analyzing identical content, with significant implications for AI deployment in polarized information environments, cross-lingual research applications, and the governance of AI systems in multilingual societies.