@article{nanonestedhumaninthelooprewardlearning,
  title = {Nano: Nested Human-in-the-Loop Reward Learning for Few-shot Language Model Control},
  author = {Xiang Fan and Yiwei Lyu and Paul Pu Liang and Ruslan Salakhutdinov and Louis-Philippe Morency},
  year = {2022},
  eprint = {2211.05750},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2211.05750v3},
}