Astro-QA

This folder was created for Astro-QA, in which the two sub-folders, `EN' and `ZH', include the English and Chinese versions of the questions, respectively. Then, the questions are organized by types in .xlsx format. For each question file, there are several key headers: 'ID' is the unique identifier of each question; 'question' denotes the body of the evaluation question; 'answer' provides the standard (reference) answer to the question; 'parse' provides a parse of the question.

If you find the dataset is useful in your research, please consider citing

@article{jieli2025astroqa,

title={An astronomical question answering dataset for evaluating large language models},

author={Jie Li, FuyongZhao, PanfengChen, JiafuXie, XiangruiZhang, Hui Li, MeiChen, YanhaoWang, MingZhu},

journal={Scientific Data},

year={2025},

url={https://doi.org/10.1038/s41597-025-04613-9}

}