LLM language alignment fails to resist Russian disinformation

A new research paper reveals that large language models fine-tuned for specific linguistic communities do not necessarily align with the expected political orientation. The study found that a Ukrainian-oriented model was less resistant to Russian disinformation when queried in Russian, while a Russian-oriented model showed stronger rejection of such narratives. The research suggests that factors like corpus composition and prompt format are more influential than nominal cultural alignment in determining an LLM's susceptibility to disinformation. AI

IMPACT Challenges the assumption that culturally aligned LLMs inherently resist disinformation, suggesting a need for more robust evaluation methods.

RANK_REASON Academic paper analyzing LLM behavior [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.CL →

• LLMs
• Russian disinformation
• Russian-oriented model
• Ukrainian-oriented model

• paper
• safety

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →