The Language You Ask In: Language-Conditioned Ideological Divergence in LLM Analysis of Contested Political Documents
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 22 of its 88 references that are in the map. First posted on arXiv 17 Jan 2026.
Builds on
22 of 88 references.
References · 22
- 2020Language Models are Few-Shot Learnerscited by 32,419
- 2023GPT-4 Technical Reportcited by 18,396
- 2022Training language models to follow instructions with human feedbackcited by 15,971
- 2019Unsupervised Cross-lingual Representation Learning at Scalecited by 3,935
- 2022BLOOM: A 176B-Parameter Open-Access Multilingual Language Modelcited by 1,984
- 2020mT5: A massively multilingual pre-trained text-to-text transformercited by 1,818
- 2020Language (Technology) is Power: A Critical Survey of "Bias" in NLPcited by 956
- 2023Whose Opinions Do Language Models Reflect?cited by 773
- 2023Open Problems and Fundamental Limitations of Reinforcement Learning from Human Feedbackcited by 759
- 2023Bias and Fairness in Large Language Models: A Surveycited by 639
- 2023Assessing Cross-Cultural Alignment between ChatGPT and Human Societies: An Empirical Studycited by 206
- 2023The political ideology of conversational AI: Converging evidence on ChatGPT's pro-environmental, left-libertarian orientationcited by 189
10 more
- 2023Generative Language Models and Automated Influence Operations: Emerging Threats and Potential Mitigationscited by 158
- 2022Probing Pre-Trained Language Models for Cross-Cultural Differences in Valuescited by 149
- 2024Measuring Political Bias in Large Language Models: What Is Said and How It Is Saidcited by 89
- 2021Mitigating Language-Dependent Ethnic Bias in BERTcited by 87
- 2024A Survey on Multilingual Large Language Models: Corpora, Alignment, and Biascited by 84
- 2020Gender Bias in Multilingual Embeddings and Cross-Lingual Transfercited by 55
- 2024Assessing Political Bias in Large Language Modelscited by 32
- 2025How malicious AI swarms can threaten democracy: The fusion of agentic AI and LLMs marks a new frontier in information warfarecited by 20
- 2024Implicit Personalization in Language Models: A Systematic Studycited by 18
- 2025Artificial Intelligence in Deliberation: The AI Penalty and the Emergence of a New Deliberative Dividecited by 4
Built on by
Citing papers per year: 2026: 1.
1 paper.