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

• URL: http://arxiv.org/abs/2606.08512v1
• Date: Sun, 07 Jun 2026 08:33:27 GMT
• Title: Friend or Foe? Language as an ideological switch in open-weight LLMs under Russian disinformation stress
• Abstract summary: We run a controlled audit of four large language models (LLMs) adapted for local post-Soviet languages.<n>We find that the Ukrainian-oriented model shows the weakest resistance to Russian disinformation in Russian.<n>We argue that the principal threat to regional information sovereignty is not adversarial fine-tuning but the untested assumption that cultural alignment guarantees resilience.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Inference-Time Steering for Cross-Lingual Factual Consistency in LLMs [51.56484100374058]
  Large Language Models (LLMs) demonstrate remarkable multilingual fluency, but their internal knowledge representations remain disproportionately biased toward high-resource languages.<n>We investigate whether these biases can be mitigated at inference time, forcing an English-prompted model to answer as if it were queried in target languages.<n>Experiments on Gemma 3 12B Instruct reveal persona prompting to be the strongest overall intervention, balancing efficacy, safety, and out-of-domain generalization.
  arXiv  Detail & Related papers  (2026-07-21T16:15:05Z)
• Schützen: Evaluating LLM Safety in Bulgarian and German Contexts [53.865251738592605]
  This paper introduces Schtzen: a German--Bulgarian safety dataset designed to assess model answerability under risk.<n> Experiments with multilingual and language-specific LLMs reveal pronounced cross-language differences in safety behavior.
  arXiv  Detail & Related papers  (2026-06-09T18:01:19Z)
• A Longitudinal, Multinational, and Multilingual Corpus of News Coverage of the Russo-Ukrainian War [4.802758600019422]
  DNIPRO is a novel longitudinal corpus of 246K news articles documenting the Russo-Ukrainian war from Feb 2022 to Aug 2024.<n>It spans eleven media outlets across five nation states (Russia, Ukraine, U.S., U.K., and China) and three languages (English, Russian, and Mandarin Chinese)
  arXiv  Detail & Related papers  (2026-01-22T20:37:42Z)
• CrossNews-UA: A Cross-lingual News Semantic Similarity Benchmark for Ukrainian, Polish, Russian, and English [53.32175252285023]
  Cross-lingual news comparison offers a promising approach to verify information.<n>Existing datasets for cross-lingual news analysis were manually curated by journalists and experts.<n>We introduce a scalable, explainable crowdsourcing pipeline for cross-lingual news similarity assessment.
  arXiv  Detail & Related papers  (2025-10-22T14:23:50Z)
• Large Language Models Reflect the Ideology of their Creators [71.65505524599888]
  Large language models (LLMs) are trained on vast amounts of data to generate natural language.<n>This paper shows that the ideological stance of an LLM appears to reflect the worldview of its creators.
  arXiv  Detail & Related papers  (2024-10-24T04:02:30Z)
• Trustworthy Alignment of Retrieval-Augmented Large Language Models via Reinforcement Learning [84.94709351266557]
  We focus on the trustworthiness of language models with respect to retrieval augmentation. We deem that retrieval-augmented language models have the inherent capabilities of supplying response according to both contextual and parametric knowledge. Inspired by aligning language models with human preference, we take the first step towards aligning retrieval-augmented language models to a status where it responds relying merely on the external evidence.
  arXiv  Detail & Related papers  (2024-10-22T09:25:21Z)
• The Adaptive Strategies of Anti-Kremlin Digital Dissent in Telegram during the Russian Invasion of Ukraine [0.6178017970021517]
  This study examines the dynamics of Anti-Kremlin content on Telegram over seven phases of the invasion. A data-driven, computational analysis of emerging topics revealed the Russian economy, combat updates, international politics, and Russian domestic affairs. Viewer approval of those events that threaten Kremlin control suggests that Telegram levels the online playing field for the opposition.
  arXiv  Detail & Related papers  (2024-08-13T18:10:06Z)
• Let Models Speak Ciphers: Multiagent Debate through Embeddings [84.20336971784495]
  We introduce CIPHER (Communicative Inter-Model Protocol Through Embedding Representation) to address this issue. By deviating from natural language, CIPHER offers an advantage of encoding a broader spectrum of information without any modification to the model weights. This showcases the superiority and robustness of embeddings as an alternative "language" for communication among LLMs.
  arXiv  Detail & Related papers  (2023-10-10T03:06:38Z)
• The Politics of Language Choice: How the Russian-Ukrainian War Influences Ukrainians' Language Use on Twitter [11.899559337707112]
  We examine language choice and tweeting activity of Ukrainian citizens based on more than 4 million geo-tagged tweets from over 62,000 users. We observe a steady shift from the Russian language towards the Ukrainian language already before the war, which drastically speeds up with its outbreak. We find that more than half of the Russian-tweeting users shift towards Ukrainian as a result of the war.
  arXiv  Detail & Related papers  (2023-05-04T12:15:54Z)
• Automated multilingual detection of Pro-Kremlin propaganda in newspapers and Telegram posts [5.886782001771578]
  The full-scale conflict between the Russian Federation and Ukraine generated an unprecedented amount of news articles and social media data. This study analyses how the media affected and mirrored public opinion during the first month of the war using news articles and Telegram news channels in Ukrainian, Russian, Romanian and English. We propose and compare two methods of multilingual automated pro-Kremlin propaganda identification, based on Transformers and linguistic features.
  arXiv  Detail & Related papers  (2023-01-25T14:25:37Z)
• "A Special Operation": A Quantitative Approach to Dissecting and Comparing Different Media Ecosystems' Coverage of the Russo-Ukrainian War [5.567674129101803]
  The coverage of the Russian invasion of Ukraine has varied widely between Western, Russian, and Chinese media ecosystems. We find that while the Western press outlets have focused on the military and humanitarian aspects of the war, Russian media have focused on the purported justifications for the "special military operation" We measure the degree to which Russian media has influenced Chinese coverage across Chinese outlets' news articles, Weibo accounts, and Twitter accounts.
  arXiv  Detail & Related papers  (2022-10-06T16:04:19Z)
• InfoBERT: Improving Robustness of Language Models from An Information Theoretic Perspective [84.78604733927887]
  Large-scale language models such as BERT have achieved state-of-the-art performance across a wide range of NLP tasks. Recent studies show that such BERT-based models are vulnerable facing the threats of textual adversarial attacks. We propose InfoBERT, a novel learning framework for robust fine-tuning of pre-trained language models.
  arXiv  Detail & Related papers  (2020-10-05T20:49:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.