@inproceedings{xia-etal-2024-aligning,
    title = "Aligning as Debiasing: Causality-Aware Alignment via Reinforcement Learning with Interventional Feedback",
    author = "Xia, Yu  and
      Yu, Tong  and
      He, Zhankui  and
      Zhao, Handong  and
      McAuley, Julian  and
      Li, Shuai",
    editor = "Duh, Kevin  and
      Gomez, Helena  and
      Bethard, Steven",
    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.naacl-long.262/",
    doi = "10.18653/v1/2024.naacl-long.262",
    pages = "4684--4695"
}