BertaQA

该数据集是一个包含英语和巴斯克语平行内容的多元选择题Trivia数据集，它既关注与巴斯克文化相关的本地问题，也包含全球范围内更广泛兴趣的问题。此外，该数据集是首例从低资源语言向高资源语言进行知识转移的可靠证据。这项任务的目的是评估语言模型在本地和全球文化知识方面的表现。

This dataset is a multiple-choice trivia dataset containing parallel content in English and Basque. It covers both local questions related to Basque culture and questions of broader interest worldwide. Moreover, this dataset represents the first credible evidence of knowledge transfer from a low-resource language to a high-resource language. The purpose of this task is to evaluate the performance of language models on both local and global cultural knowledge.