@inproceedings{dinh2024sciex,
  title={SciEx: Benchmarking Large Language Models on Scientific Exams with Human Expert Grading and Automatic Grading},
  author={Dinh, Tu and Mullov, Carlos and B{\"a}rmann, Leonard and Li, Zhaolin and Liu, Danni and Rei{\ss}, Simon and Lee, Jueun and Lerzer, Nathan and Gao, Jianfeng and Peller-Konrad, Fabian and others},
  booktitle={Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing},
  pages={11592--11610},
  year={2024}
}