FreedomIntelligence/Ar-BeaverTails-Evaluation
收藏Hugging Face2024-11-14 更新2025-04-08 收录
下载链接：
https://hf-mirror.com/datasets/FreedomIntelligence/Ar-BeaverTails-Evaluation
下载链接
链接失效反馈官方服务：
资源简介：
BeaverTails-Evaluation阿拉伯语版本是一个用于评估大型语言模型安全性的数据集，包含可能引发模型生成冒犯性语言的提示，以帮助确定模型在面对冒犯性问题时是否能维持人类价值观。
The Arabic version of BeaverTails-Evaluation is a dataset designed to assess the safety of large language models by containing prompts that are likely to provoke the model into generating offensive language, in order to determine whether the model can maintain human values when faced with offensive questions.
提供机构：
FreedomIntelligence
