@article{benchmarkinglargelanguagemodelson2,
  title = {Benchmarking Large Language Models on Answering and Explaining Challenging Medical Questions},
  author = {Hanjie Chen and Zhouxiang Fang and Yash Singla and Mark Dredze},
  year = {2024},
  eprint = {2402.18060},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.18060v5},
}