@article{metarewardinglanguagemodelsselfimproving,
  title = {Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge},
  author = {Tianhao Wu and Weizhe Yuan and Olga Golovneva and Jing Xu and Yuandong Tian and Jiantao Jiao and Jason Weston and Sainbayar Sukhbaatar},
  year = {2024},
  eprint = {2407.19594},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.19594v2},
}