نسخة أولية وصول مفتوح
ACTR: Aligning Thoughts and Responses for Multilingual Safety in Reasoning LLMs
Ensuring the safety of reasoning large language models (LLMs) across languages is essential for their reliable deployment. However, when exposed to jailbreak attacks in non-high-resource languages, these models may generate unsafe responses even when their reasoning traces identify safety risks. To address this issue, …