@article{rlhsmitigatingmisalignmentinrlhfwith,
  title = {RLHS: Mitigating Misalignment in RLHF with Hindsight Simulation},
  author = {Kaiqu Liang and Haimin Hu and Ryan Liu and Thomas L. Griffiths and Jaime Fernández Fisac},
  year = {2025},
  eprint = {2501.08617},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2501.08617v1},
}