@article{ichihara-etal-2026-mo,
    title = "{MO}-{GRPO}: Mitigating Reward Hacking of Group Relative Policy Optimization on Multi-Objective Problems",
    author = "Ichihara, Yuki  and
      Jinnai, Yuu  and
      Morimura, Tetsuro  and
      Sakamoto, Mitsuki  and
      Mitsuhashi, Ryota  and
      Uchibe, Eiji",
    journal = "Transactions of the Association for Computational Linguistics",
    volume = "14",
    year = "2026",
    address = "Cambridge, MA",
    publisher = "MIT Press",
    url = "https://aclanthology.org/2026.tacl-1.84/",
    doi = "10.1162/tacl.a.782",
    pages = "1867--1882"
}