@article{howreliableareautomaticevaluationmethods,
  title = {How Reliable Are Automatic Evaluation Methods for Instruction-Tuned LLMs?},
  author = {Ehsan Doostmohammadi and Oskar Holmström and Marco Kuhlmann},
  year = {2024},
  eprint = {2402.10770},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2402.10770v4},
}