Minionese: Comprehensive Benchmark and Mechanistic Study of Multilingual LLM Safety

Jul 14, 2026

Researchers introduce Minionese, a multilingual jailbreak benchmark that spans 18 languages, 4 resource tiers, and 4 perturbation types to evaluate the safety alignment of large language models (LLMs). The study finds that prompts refused in English can elicit harmful responses in non-English and low-resource languages, with each attack type exposing distinct vulnerabilities. Mechanistic analysis reveals that low-resource jailbreaks exploit geometric misalignments in model representations, bypassing refusal mechanisms without disabling them.

Why it matters: This work demonstrates that evaluating LLM safety solely in English is inadequate, emphasizing the need for multilingual and script-aware safety assessments.

Full story at: arXiv Cryptography and Security ↗