@article{tpoaligninglargelanguagemodelswithmulti,
  title = {TPO: Aligning Large Language Models with Multi-branch & Multi-step Preference Trees},
  author = {Weibin Liao and Xu Chu and Yasha Wang},
  year = {2024},
  eprint = {2410.12854},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2410.12854v1},
}