@article{whencanwetrustllmgraderscalibratingconfi,
  title = {When Can We Trust LLM Graders? Calibrating Confidence for Automated Assessment},
  author = {Robinson Ferrer and Damla Turgut and Zhongzhou Chen and Shashank Sonkar},
  year = {2026},
  eprint = {2603.29559},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2603.29559},
}