# Friend or Foe? Language as an ideological switch in open-weight LLMs under Russian disinformation stress

arXiv: https://arxiv.org/abs/2606.08512 · HTML: https://mlsanity.com/paper/2606.08512/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 20 references that are in the map.
- First posted on arXiv 7 Jun 2026.

## Builds on (most cited first, 6 of 6)

- [Political Compass or Spinning Arrow? Towards More Meaningful Evaluations for Values and Opinions in Large Language Models](https://mlsanity.com/paper/2402.16786/) (2024)
- [Having Beer after Prayer? Measuring Cultural Bias in Large Language Models](https://mlsanity.com/paper/2305.14456/) (2023)
- [Factuality Challenges in the Era of Large Language Models](https://mlsanity.com/paper/2310.05189/) (2023)
- [The Political Preferences of LLMs](https://mlsanity.com/paper/2402.01789/) (2024)
- [OpinionGPT: Modelling Explicit Biases in Instruction-Tuned LLMs](https://mlsanity.com/paper/2309.03876/) (2023)
- [Laboratory-Scale AI: Open-Weight Models are Competitive with ChatGPT Even in Low-Resource Settings](https://mlsanity.com/paper/2405.16820/) (2024)

## Abstract (arXiv)

As Russia's war against Ukraine extends into generative AI, large language models (LLMs) adapted for local post-Soviet languages are deployed in contested information environments. Policy and industry discourse assumes that culturally aligned adaptation encodes the political orientation of the target community: a Ukrainian-oriented model will resist Russian narratives, a Russian-oriented one will reinforce them. Does it? This article systematically disconfirms that assumption. We run a controlled audit of four openly available LLMs sharing a common base model but fine-tuned for different linguistic communities, querying them in Ukrainian, Russian and English across ten contested wartime narratives: Crimea, "denazification", the "one people" thesis, and atrocity denial at Bucha and Mariupol. The result is a Fine-Tuning Paradox: the Ukrainian-oriented model shows the weakest resistance to Russian disinformation in Russian, while the Russian-oriented one exhibits the strongest rejection. Corpus composition, language coverage and prompt format prove more decisive than nominal cultural provenance. We situate these findings within debates on hybrid warfare, digital sovereignty and post-imperial information orders, arguing that the principal threat to regional information sovereignty is not adversarial fine-tuning but the untested assumption that cultural alignment guarantees resilience.