@inproceedings{havrilla-etal-2023-trlx,
    title = "trl{X}: A Framework for Large Scale Reinforcement Learning from Human Feedback",
    author = "Havrilla, Alexander  and
      Zhuravinskyi, Maksym  and
      Phung, Duy  and
      Tiwari, Aman  and
      Tow, Jonathan  and
      Biderman, Stella  and
      Anthony, Quentin  and
      Castricato, Louis",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2023.emnlp-main.530/",
    doi = "10.18653/v1/2023.emnlp-main.530",
    pages = "8578--8595"
}