@article{inverseqtokenlevelreinforcementlearning,
  title = {Inverse-Q*: Token Level Reinforcement Learning for Aligning Large Language Models Without Preference Data},
  author = {Han Xia and Songyang Gao and Qiming Ge and Zhiheng Xi and Qi Zhang and Xuanjing Huang},
  year = {2024},
  eprint = {2408.14874},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2408.14874v2},
}