@article{llmsinsteadofhumanjudgesalargescale,
  title = {LLMs instead of Human Judges? A Large Scale Empirical Study across 20 NLP Evaluation Tasks},
  author = {Anna Bavaresco and Raffaella Bernardi and Leonardo Bertolazzi and Desmond Elliott and Raquel Fernández and Albert Gatt and Esam Ghaleb and Mario Giulianelli and Michael Hanna and Alexander Koller and André F. T. Martins and Philipp Mondorf and Vera Neplenbroek and Sandro Pezzelle and Barbara Plank and David Schlangen and Alessandro Suglia and Aditya K Surikuchi and Ece Takmaz and Alberto Testoni},
  year = {2024},
  eprint = {2406.18403},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.18403v2},
}