MSafeTemp：覆盖60种语言的多语言安全对齐数据集
How I Aligned Your Model: Scaling Up Multilingual Safety Training with Templates
安全对齐数据基本只有英文，这篇提出了模板增强的办法，做出覆盖60种语言的MSafeTemp数据集，还证明英文评测根本测不出多语言漏洞。
一篇arXiv论文提出了基于模板的多语言安全训练数据增强管线：从有害提示中提取安全模板，翻译后用文化本地化的实体填充，生成拒绝语料和良性语料。作者据此发布MSafeTemp数据集，覆盖60种语言，可用于多语言安全对齐与评测。实验显示仅用英文评测会误判多语言安全性：若干模型在英文中防御成功的攻击，翻译成其他语言后即告得手，而文化本地化变体还会暴露更多翻译测试漏掉的漏洞。用模板增强安全训练数据后，模型在英语之外语言上的安全表现得到提升。
How I Aligned Your Model: Scaling Up Multilingual Safety Training with Templates
Safety alignment for Large Language Models is heavily focused on English with limited multilingual representation, particularly damaging low-resource language performance. Related open training datasets are often limited in size or do not follow region-localized harmful topics to broaden the scope of alignment beyond cultures. We propose a scalable template-based augmentation pipeline to produce massive multilingual refusal and benign corpora, extracting safe templates from harmful prompts, translating them and then filling in the slots with culturally authentic entities, both harmful and benign. As a result, we release MSafeTemp, a validated corpus spanning 60 languages useful for multilingual safety alignment and evaluation. Using the dataset, we show that English-only evaluation misjudges multilingual safety: for several models, attacks that fail in English succeed once translated, while culturally localized variants expose further failures that translation alone misses. We also confirm that augmenting safety training data through templates allows for higher diversity and quality of alignment, resulting in improved safety performance beyond English. MSafeTemp and the respective pipeline are aimed at facilitating research and development of safer and more responsible models for less-represented cultures.