@article{rewardmodelingformitigatingtoxicityin,
  title = {Reward Modeling for Mitigating Toxicity in Transformer-based Language Models},
  author = {Farshid Faal and Ketra Schmitt and Jia Yuan Yu},
  year = {2022},
  eprint = {2202.09662},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2202.09662v6},
}