@article{catastrophicgoodhartregularizingrlhfwith,
  title = {Catastrophic Goodhart: regularizing RLHF with KL divergence does not mitigate heavy-tailed reward misspecification},
  author = {Thomas Kwa and Drake Thomas and Adrià Garriga-Alonso},
  year = {2024},
  eprint = {2407.14503},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2407.14503v2},
}