shalanova/benchmark-1-chinese-m2m

该数据集是通过facebook/m2m100_418M模型翻译成中文的，来源于jayavibhav/prompt-injection-safety。主要包含prompt-injection和典型的jailbreak-style指令，具有相对同质的攻击模式。数据集大小为1,000个提示（500个安全/500个不安全）。包含的列有text（原始提示）、label（0表示安全，1表示不安全）、translation（由facebook/m2m100_418M翻译的中文提示）和score_zh_model（与codebook的余弦相似度分数）。更多信息可以参考提供的论文链接。

The dataset is translated into Chinese by the facebook/m2m100_418M model and sourced from jayavibhav/prompt-injection-safety. It primarily contains prompt-injection and canonical jailbreak-style instructions with relatively homogeneous attack patterns. The dataset size is 1,000 prompts (500 safe / 500 unsafe). Columns include text (original prompt), label (0: safe, 1: unsafe), translation (prompt in Chinese translated by facebook/m2m100_418M), and score_zh_model (cosine similarity score with codebook). More information can be found in the provided paper link.