EnviroExam
Benchmarking Environmental Science Knowledge
of Large Language Models
(2024)
EnviroExam is a comprehensive evaluation method designed to assess the knowledge of large language models in the field of environmental science. It is based on the curricula of top international universities and includes 936 questions across 42 core courses, covering undergraduate, master's, and doctoral levels.
EnviroExam includes 936 questions across 42 core courses, encompassing a wide range of environmental science subjects.
Our data can be directly downloaded on Huggingface datasets. Please refer to our github instructions for how to read and use the data.
@misc{huang2024enviroexam,
title={EnviroExam: Benchmarking Environmental Science Knowledge of Large Language Models},
author={Yu Huang and Liang Guo and Wanqian Guo and Zhe Tao and Yang Lv and Zhihao Sun and Dongfang Zhao},
year={2024},
eprint={2405.11265},
archivePrefix={arXiv},
primaryClass={cs.CL}
}
1School of environment, Harbin institute of technology
Have any questions about EnviroExam? Please contact us at enviroscientistoffical@gmail.com or create an issue on Github. For potential collaboration, please contact 23s129119@stu.hit.edu.cn.
