BIOPARS-BENCH
收藏arXiv2025-09-30 收录
下载链接：
https://github.com/amirap80/BioPars
下载链接
链接失效反馈官方服务：
资源简介：
该数据集包含了超过10,000篇科学文章、教科书以及医学网站的内容，它是BioPars项目的一部分，该项目旨在提升波斯语医学问答系统的性能。该数据集的任务是对生物医药文本进行挖掘，并对大型语言模型进行评估。
This dataset contains over 10,000 pieces of content sourced from scientific articles, textbooks, and medical websites. It is part of the BioPars project, which aims to improve the performance of Persian-language medical question answering systems. The core tasks of this dataset involve biomedical text mining and the evaluation of large language models (LLMs).
提供机构：
Authors of the paper
