AI RESEARCH
CREST: Universal Safety Guardrails Through Cluster-Guided Cross-Lingual Transfer
arXiv CS.LG
•
ArXi:2512.02711v2 Announce Type: replace-cross Ensuring content safety in large language models (LLMs) is essential for their deployment in real-world applications. However, existing safety guardrails are predominantly tailored for high-resource languages, leaving a significant portion of the world's population underrepresented who communicate in low-resource languages. To address this, we