@article{dl-19-1,
  title = {{Rank Analysis of Incomplete Block Designs: I. The Method of Paired Comparisons}},
  author = {Bradley, Ralph Allan and Terry, Milton E.},
  journal = {Biometrika},
  year = {1952},
  doi = {10.2307/2334029},
  url = {https://www.jstor.org/stable/2334029}
}

@inproceedings{dl-19-2,
  title = {{Deep Reinforcement Learning from Human Preferences}},
  author = {Christiano, Paul F. and Leike, Jan and Brown, Tom B. and Martic, Miljan and Legg, Shane and Amodei, Dario},
  booktitle = {Advances in Neural Information Processing Systems 30},
  year = {2017},
  url = {https://proceedings.neurips.cc/paper/2017/hash/d5e2c0adad503c91f91df240d0cd4e49-Abstract.html}
}

@inproceedings{dl-19-3,
  title = {{Direct Preference Optimization: Your Language Model is Secretly a Reward Model}},
  author = {Rafailov, Rafael and Sharma, Archit and Mitchell, Eric and Ermon, Stefano and Manning, Christopher D. and Finn, Chelsea},
  booktitle = {Advances in Neural Information Processing Systems 36},
  year = {2023},
  doi = {10.52202/075280-2338},
  url = {https://proceedings.neurips.cc/paper_files/paper/2023/hash/a85b405ed65c6477a4fe8302b5e06ce7-Abstract.html}
}