@article{auditingllmbenchmarkswithitemresponsethe,
  title = {Auditing LLM Benchmarks with Item Response Theory},
  author = {Sander Land and Daniel M. Bikel},
  year = {2026},
  eprint = {2605.30504},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2605.30504},
}