The Illusion of Cross-Lingual Safety in Low-Resource Languages

Safety alignment in large language models (LLMs) is largely developed in English, assuming these safeguards generalize across multilingual settings.

Safety alignment in large language models (LLMs) is largely developed in English, assuming these safeguards generalize across multilingual settings. However, this assumption remains underexplored and exposes a vulnerability in low-resource languages. We investigate cross-lingual…