@article{evaluatingtheperformanceandfragilityof,
  title = {Evaluating the performance and fragility of large language models on the self-assessment for neurological surgeons},
  author = {Krithik Vishwanath and Anton Alyakin and Mrigayu Ghosh and Jin Vivian Lee and Daniel Alexander Alber and Karl L. Sangwon and Douglas Kondziolka and Eric Karl Oermann},
  year = {2025},
  eprint = {2505.23477},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2505.23477v1},
}