@article{evaluatingtheperformanceoflargelanguage2,
  title = {Evaluating the Performance of Large Language Models via Debates},
  author = {Behrad Moniri and Hamed Hassani and Edgar Dobriban},
  year = {2024},
  eprint = {2406.11044},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2406.11044v1},
}