@inproceedings{du-etal-2024-rewarding,
    title = "Rewarding What Matters: Step-by-Step Reinforcement Learning for Task-Oriented Dialogue",
    author = "Du, Huifang  and
      Li, Shuqin  and
      Wu, Minghao  and
      Feng, Xuejing  and
      Li, Yuan-Fang  and
      Wang, Haofen",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.findings-emnlp.472/",
    doi = "10.18653/v1/2024.findings-emnlp.472",
    pages = "8030--8046"
}