@article{lu-etal-2026-learning,
    title = "Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting",
    author = "Lu, Yining  and
      Wang, Zilong  and
      Li, Shiyang  and
      Liu, Xin  and
      Yu, Changlong  and
      Yin, Qingyu  and
      Shi, Zhan  and
      Zhang, Zixuan  and
      Jiang, Meng",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "14",
    year = "2026",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://aclanthology.org/2026.tacl-1.47/",
    doi = "10.1162/tacl.a.696",
    pages = "1051--1073"
}