@inproceedings{yoon-etal-2024-tlcr,
    title = "{TLCR}: Token-Level Continuous Reward for Fine-grained Reinforcement Learning from Human Feedback",
    author = "Yoon, Eunseop  and
      Yoon, Hee Suk  and
      Eom, SooHwan  and
      Han, Gunsoo  and
      Nam, Daniel  and
      Jo, Daejin  and
      On, Kyoung-Woon  and
      Hasegawa-Johnson, Mark  and
      Kim, Sungwoong  and
      Yoo, Chang",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2024",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.findings-acl.889/",
    doi = "10.18653/v1/2024.findings-acl.889",
    pages = "14969--14981"
}