@article{sampleefficientreinforcementlearningfrom,
  title = {Sample Efficient Preference Alignment in LLMs via Active Exploration},
  author = {Viraj Mehta and Syrine Belakaria and Vikramjeet Das and Ojash Neopane and Yijia Dai and Ilija Bogunovic and Barbara Engelhardt and Stefano Ermon and Jeff Schneider and Willie Neiswanger},
  year = {2023},
  eprint = {2312.00267},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2312.00267v3},
}