BenchmarkJune 16, 20261 min read
AI Models Exposed: 60% Fail to Detect Russian Propaganda in New Benchmark
A new benchmark has revealed that many AI language models are vulnerable to Russian propaganda, with some models scoring as low as 1 out of 5 in detecting disinformation. The results have significant implications for developers, businesses, and everyday users who rely on these models for accurate information.
The Institute of the Estonian Language has released a benchmark measuring how susceptible AI language models are to Russian propaganda. The article How easily can Russian propaganda fool AI models? A new benchmark finds out appeared first on The Decoder.