AlbanianLLMSafety: A Safety Evaluation Dataset for Large Language Models in Albanian 事件

AlbanianLLMSafety: A Safety Evaluation Dataset for Large Language Models in Albanian arXiv:2605.26954v1 Announce Type: new Abstract: Safety evaluation of Large Language Models (LLMs) has largely focused on high-resource languages, leaving low-resource languages critically underserved. We present AlbanianLLMSafety, the first publicly available safety evaluation dataset for LLMs in Albanian, a linguistically distinct low-resource language with approximately 7.5 million speakers across Albania, Ko