mlsanityData to 14 Oct 2026

Do Political Opinions Transfer Between Western Languages? An Analysis of Unaligned and Aligned Multilingual LLMs

arXiv 2508.05553 ↗First posted 7 Aug 2025cs.CL cs.CYcited by 6

On the map: LLM alignment / RLHF / preference optimisation → Human values and AI feedback alignment

Abstract (arXiv)

Public opinion surveys show cross-cultural differences in political opinions between socio-cultural contexts. However, there is no clear evidence whether these differences translate to cross-lingual differences in multilingual large language models (MLLMs). We analyze whether opinions transfer between languages or whether there are separate opinions for each language in MLLMs of various sizes across five Western languages. We evaluate MLLMs' opinions by prompting them to report their (dis)agreement with political statements from voting advice applications. To better understand the interaction between languages in the models, we evaluate them both before and after aligning them with more left or right views using direct preference optimization and English alignment data only. Our findings reveal that unaligned models show only very few significant cross-lingual differences in the political opinions they reflect. The political alignment shifts opinions almost uniformly across all five languages. We conclude that in Western language contexts, political opinions transfer between languages, demonstrating the challenges in achieving explicit socio-linguistic, cultural, and political alignment of MLLMs.

Key facts. Cited by 6 papers in the map (data through 14 Oct 2026). Placed in Human values and AI feedback alignment, one of 10 directions in LLM alignment / RLHF / preference optimisation. Builds on 19 of its 37 references that are in the map. First posted on arXiv 7 Aug 2025.

Builds on

19 of 37 references.

References · 19

  1. 2024The Llama 3 Herd of Modelscited by 14,715
  2. 2023Direct Preference Optimization: Your Language Model is Secretly a Reward Modelcited by 8,065
  3. 2019Fine-Tuning Language Models from Human Preferencescited by 2,150
  4. 2024Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phonecited by 1,917
  5. 2023Whose Opinions Do Language Models Reflect?cited by 773
  6. 2020CrowS-Pairs: A Challenge Dataset for Measuring Social Biases in Masked Language Modelscited by 710
  7. 2021BBQ: A Hand-Built Bias Benchmark for Question Answeringcited by 701
  8. 2024Aya Model: An Instruction Finetuned Open-Access Multilingual Language Modelcited by 295
  9. 2023From Pretraining Data to Language Models to Downstream Tasks: Tracking the Trails of Political Biases Leading to Unfair NLP Modelscited by 260
  10. 2024Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Modelscited by 162
  11. 2023Do Multilingual Language Models Think Better in English?cited by 88
  12. 2024A Survey on Multilingual Large Language Models: Corpora, Alignment, and Biascited by 84
7 more
  1. 2024Hidden Persuaders: LLMs' Political Leaning and Their Influence on Voterscited by 71
  2. 2023PolyLM: An Open Source Polyglot Large Language Modelcited by 64
  3. 2024Beyond prompt brittleness: Evaluating the reliability and consistency of political worldviews in LLMscited by 55
  4. 2023Comparing Biases and the Impact of Multilingual Training across Multiple Languagescited by 36
  5. 2024MBBQ: A Dataset for Cross-Lingual Comparison of Stereotypes in Generative LLMscited by 35
  6. 2025IssueBench: Millions of Realistic Prompts for Measuring Issue Bias in LLM Writing Assistancecited by 26
  7. 2024Llama meets EU: Investigating the European Political Spectrum through the Lens of LLMscited by 14

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 1; 2026: 5.

6 papers.

  1. 2025What Is The Political Content in LLMs' Pre- and Post-Training Data?cited by 7
  2. 2026Beyond Marginal Distributions: A Framework to Evaluate the Representativeness of Demographic-Aligned LLMscited by 4
  3. 2026Finding Sense in Nonsense with Generated Contexts: Perspectives from Humans and Language Modelscited by 0
  4. 2026SommBench: Assessing Sommelier Expertise of Language Modelscited by 0
  5. 2026Large Language Models are Perplexed by some Political Partiescited by 0
  6. 2026WildSEEK: Evaluating Language Models for Information-Seekingcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Mind the Gap: Pitfalls of LLM Alignment with Asian Public Opinion
  2. 2025On the Alignment of Large Language Models with Global Human Opinion
  3. 2025Examining Alignment of Large Language Models through Representative Heuristics: The Case of Political Stereotypes
  4. 2025Multilingual != Multicultural: Evaluating Gaps Between Multilingual Capabilities and Cultural Alignment in LLMs
  5. 2026Political Alignment in Large Language Models: A Multidimensional Audit of Psychometric Identity and Behavioral Bias
  6. 2023Towards Measuring the Representation of Subjective Global Opinions in Language Models
  7. 2026Navigating the digital spectrum: Assessing political bias, stability, and downstream fairness in Large Language Models
  8. 2026Who Would You Vote For? Auditing Political Alignment in LLMs: An Italian Case-Study