Skip to main content

🏢 TU Darmstadt

LLMs Lost in Translation: M-ALERT uncovers Cross-Linguistic Safety Gaps
·11623 words·55 mins· loading · loading
AI Generated 🤗 Daily Papers Natural Language Processing Large Language Models 🏢 TU Darmstadt
M-ALERT, a new multilingual benchmark, reveals significant safety inconsistencies across languages in top LLMs.