@article{elouncoveredrobustnessandbestpractices,
  title = {Elo Uncovered: Robustness and Best Practices in Language Model Evaluation},
  author = {Meriem Boubdir and Edward Kim and Beyza Ermis and Sara Hooker and Marzieh Fadaee},
  year = {2023},
  eprint = {2311.17295},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2311.17295v1},
}