@article{reinforcementlearningwithtokenlevel,
  title = {Reinforcement Learning with Token-level Feedback for Controllable Text Generation},
  author = {Wendi Li and Wei Wei and Kaihe Xu and Wenfeng Xie and Dangyang Chen and Yu Cheng},
  year = {2024},
  eprint = {2403.11558},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2403.11558v1},
}