@article{Guo2024direct,
  title={Direct Language Model Alignment from Online AI Feedback},
  author={Guo, Shangmin and Zhang, Biao and Liu, Tianlin and Liu, Tianqi and Khalman, Misha and Llinares-L{\'o}pez, Felipe and Ram{\'e}, Alexandre and Mesnard, Thomas and Zhao, Yao and Piot, Bilal and Ferret, Johan and Blondel, Mathieu},
  journal={arXiv preprint arXiv:2402.04792},
  year={2024}
}
