ESTONIAN TEST RANKS LLMS ON RUSSIAN PROPAGANDA

Estonia's government released findings from a comprehensive study testing LLMs against Russian propaganda techniques. The benchmark assessed models' resilience to what researchers call "strategic narratives"—coordinated disinformation campaigns designed to influence public opinion. Key findings show performance gaps across leading models. Some LLMs demonstrated stronger resistance to propaganda framing, while others proved more susceptible to manipulation or biased outputs. The Estonian government designed the evaluation to address growing concerns about AI systems amplifying geopolitical disinformation. Russia's information warfare campaigns have targeted NATO members, including the Baltic states, making this research particularly relevant for regional security. Results can help organizations select models less prone to propagating false narratives. The benchmark also identifies specific vulnerabilities in current systems, providing data for developers working to improve AI robustness against sophisticated disinformation. As LLMs become integral to content filtering and information platforms, resistance to coordinated propaganda campaigns increasingly matters for democratic institutions and public discourse.