@article{medicallargelanguagemodelbenchmarks,
  title = {Medical Large Language Model Benchmarks Should Prioritize Construct Validity},
  author = {Ahmed Alaa and Thomas Hartvigsen and Niloufar Golchini and Shiladitya Dutta and Frances Dean and Inioluwa Deborah Raji and Travis Zack},
  year = {2025},
  eprint = {2503.10694},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2503.10694v1},
}