@inproceedings{fan-etal-2023-nano,
    title = "Nano: Nested Human-in-the-Loop Reward Learning for Few-shot Language Model Control",
    author = "Fan, Xiang  and
      Lyu, Yiwei  and
      Liang, Paul Pu  and
      Salakhutdinov, Ruslan  and
      Morency, Louis-Philippe",
    editor = "Rogers, Anna  and
      Boyd-Graber, Jordan  and
      Okazaki, Naoaki",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2023.findings-acl.758/",
    doi = "10.18653/v1/2023.findings-acl.758",
    pages = "11970--11992"
}