@misc{henkel2024large,
  title={Can Large Language Models Make the Grade? An Empirical Study Evaluating LLMs Ability to Mark Short Answer Questions in K-12 Education},
  author={Owen Henkel and Adam Boxer and Libby Hills and Bill Roberts},
  year={2024},
  eprint={2405.02985},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2405.02985}
}