@inproceedings{khaki-etal-2024-rs,
    title = "{RS}-{DPO}: A Hybrid Rejection Sampling and Direct Preference Optimization Method for Alignment of Large Language Models",
    author = "Khaki, Saeed  and
      Li, JinJin  and
      Ma, Lan  and
      Yang, Liu  and
      Ramachandra, Prathap",
    editor = "Duh, Kevin  and
      Gomez, Helena  and
      Bethard, Steven",
    booktitle = "Findings of the Association for Computational Linguistics: NAACL 2024",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.findings-naacl.108/",
    doi = "10.18653/v1/2024.findings-naacl.108",
    pages = "1665--1680"
}