sapienzanlp/mmlu_italian
收藏Hugging Face2025-12-02 更新2024-07-22 收录
下载链接：
https://hf-mirror.com/datasets/sapienzanlp/mmlu_italian
下载链接
链接失效反馈官方服务：
资源简介：
MMLU - Italian (IT)数据集是Massive Multitask Language Understanding (MMLU)的意大利语翻译版本，包含来自57个不同主题的多项选择题，旨在评估模型在广泛主题上的回答能力。数据集包括验证集和测试集，分别包含1,478和13,541行数据。与原始数据集相比，此版本对实例进行了分类，并减少了部分实例。数据集完全并行于英语和意大利语，使用开源工具OBenTO-LLM进行翻译。数据集格式包括唯一ID、任务类型、原始英语句子、意大利语翻译、选项、选项翻译、正确答案索引和元数据。
This dataset is an Italian translation of Massive Multitask Language Understanding (MMLU), containing multiple-choice questions from 57 different topics. Each question has one correct answer and three distractors, with the task being to predict the correct answer. The dataset includes validation and test sets, and is fully parallel between English and Italian. The translation process used the open-source tool OBenTO-LLM to ensure the openness and transparency of the research.
提供机构：
sapienzanlp
