朋友还是敌人？俄罗斯虚假信息压力下开放权重大语言模型中的语言意识形态开关
Friend or Foe? Language as an ideological switch in open-weight LLMs under Russian disinformation stress
AI总结：
本文通过控制实验发现，针对不同语言社区微调的大语言模型在俄罗斯虚假信息压力下，其抵抗能力与预期文化对齐方向相反，揭示了微调悖论。
摘要：
随着俄罗斯对乌克兰的战争扩展到生成式人工智能，针对当地后苏联语言进行调整的大语言模型被部署在有争议的信息环境中。政策和行业话语假设，文化对齐的调整编码了目标社区的政治取向：乌克兰导向的模型将抵制俄罗斯叙事，俄罗斯导向的模型将强化它们。果真如此吗？本文系统地否定了这一假设。我们对四个共享相同基础模型但针对不同语言社区微调的公开可用大语言模型进行了受控审计，用乌克兰语、俄语和英语查询它们关于十个有争议的战争叙事：克里米亚、“去纳粹化”、“一个民族”论以及布查和马里乌波尔的暴行否认。结果是一个微调悖论：乌克兰导向的模型在俄语中对俄罗斯虚假信息的抵抗最弱，而俄罗斯导向的模型表现出最强的拒绝。语料库构成、语言覆盖范围和提示格式被证明比名义上的文化来源更具决定性。我们将这些发现置于混合战争、数字主权和后帝国信息秩序的辩论中，认为对区域信息主权的主要威胁不是对抗性微调，而是未经检验的假设，即文化对齐能保证韧性。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
