The Language You Ask In: Language-Conditioned Ideological Divergence in LLM Analysis of Contested Political Documents
For users and developers of multilingual LLMs, this demonstrates that model outputs on politically contested texts can vary systematically by prompt language, undermining claims of neutrality and raising challenges for pluralistic alignment.
LLMs like ChatGPT 5.2 and Claude Opus 4.5 show language-conditioned ideological divergence when analyzing contested political documents: Russian prompts elicit delegitimizing readings, while Ukrainian prompts elicit legitimizing ones, with neither model neutral. This reveals that models silently adopt the dominant frame of the prompt's language rather than surfacing multiple interpretive traditions.
Large language models are increasingly used to interpret politically contested questions, value-laden material on which there is no single correct answer, only competing interpretive traditions. We ask whether a model's choice among those traditions can turn on the language of the prompt rather than the content. Comparing two frontier models, ChatGPT 5.2 and Claude Opus 4.5, on one contested Ukrainian civil-society document under semantically matched Russian and Ukrainian prompts, we find that both shift along the same axis on identical source text: Russian prompts elicit delegitimizing readings of the document's authors and Ukrainian prompts legitimating ones. The magnitude is model-dependent but neither model is neutral: each adopts a language-dependent stance, and the difference is one of degree. Because contested political questions admit no correct reading against which to measure, we read this as language-conditioned variation in which interpretive tradition a model activates: the model neither holds a single stance nor surfaces the plurality of available ones, but silently adopts the dominant frame of the prompt's language. We draw out the consequences for pluralism-aware evaluation, which must probe the same content across the languages a model serves, and for pluralistic alignment in multilingual settings.