mteb/mFollowIRCrossLingual
收藏Hugging Face2025-10-21 更新2025-10-25 收录
下载链接：
https://hf-mirror.com/datasets/mteb/mFollowIRCrossLingual
下载链接
链接失效反馈官方服务：
资源简介：
mFollowIRCrossLingual是一个多语言文本嵌入基准数据集，用于评估检索指令遵循能力。该数据集包括波斯语、俄语和中文，使用英语查询/指令。数据集包含不同语言对的多种配置，并提供有关样本数量、字符数、文本长度、相关文档和每个语言对排名前文档的统计数据。
mFollowIRCrossLingual is a multilingual text embedding benchmark dataset designed to measure retrieval instruction following ability. The dataset includes Farsi, Russian, and Chinese languages with English queries/instructions. It features various configurations for different language pairs and provides statistics on the number of samples, characters, text length, relevant documents, and top-ranked documents for each language pair. The dataset is available for download and can be evaluated using the provided code snippet.
提供机构：
mteb
