@inproceedings{li-etal-2024-reinforcement,
    title = "Reinforcement Learning with Token-level Feedback for Controllable Text Generation",
    author = "Li, Wendi  and
      Wei, Wei  and
      Xu, Kaihe  and
      Xie, Wenfeng  and
      Chen, Dangyang  and
      Cheng, Yu",
    editor = "Duh, Kevin  and
      Gomez, Helena  and
      Bethard, Steven",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/Author-page-Marten-During-lu/2024.findings-naacl.111/",
    doi = "10.18653/v1/2024.findings-naacl.111",
    pages = "1704--1719"
}