@article{diverseandeffectiveredteamingwithauto,
  title = {Diverse and Effective Red Teaming with Auto-generated Rewards and Multi-step Reinforcement Learning},
  author = {Alex Beutel and Kai Xiao and Johannes Heidecke and Lilian Weng},
  year = {2024},
  eprint = {2412.18693},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2412.18693v1},
}