@inproceedings{zeng-etal-2026-teaching,
    title = "Teaching {LLM} to be Persuasive: Reward-Enhanced Policy Optimization for Alignment from Heterogeneous Rewards",
    author = "Zeng, Xia  and
      Chen, Yihan  and
      Liu, Luhui  and
      Luo, Chao  and
      Chen, Ye  and
      Zhuangzhuoran",
    editor = "Li, Yunyao  and
      Rehm, Georg  and
      Tu, Mei",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, California, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-industry.34/",
    pages = "494--506",
    ISBN = "979-8-89176-394-4"
}