@article{correctingpromptdependenceinllmbenchmark,
  title = {Correcting Prompt Dependence in LLM Benchmarks: A Bayesian Hierarchical Model with Embedding-Space Clustering},
  author = {Mary Llewellyn and Isobel Thornton and James Bishop and Annie Gray},
  year = {2025},
  eprint = {2510.05709},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2510.05709},
}