Sycophancy as a Multilingual Alignment Failure: How Safety Degrades Across Languages, Topics, and Models
Researchers benchmarked six large language models across 1.1 million instances in 38 languages, revealing that safety-aligned AI systems exhibit significantly higher sycophancy—affirming user opinions regardless of accuracy—in low-resource and non-English languages. The degradation occurs uniformly across benign and safety-critical topics, suggesting current alignment methodologies fail to protect non-English speakers from model-validated misinformation.