BibTeX record journals/corr/abs-2307-04964

download as .bib file

@article{DBLP:journals/corr/abs-2307-04964,
  author       = {Rui Zheng and
                  Shihan Dou and
                  Songyang Gao and
                  Yuan Hua and
                  Wei Shen and
                  Binghai Wang and
                  Yan Liu and
                  Senjie Jin and
                  Qin Liu and
                  Yuhao Zhou and
                  Limao Xiong and
                  Lu Chen and
                  Zhiheng Xi and
                  Nuo Xu and
                  Wenbin Lai and
                  Minghao Zhu and
                  Cheng Chang and
                  Zhangyue Yin and
                  Rongxiang Weng and
                  Wensen Cheng and
                  Haoran Huang and
                  Tianxiang Sun and
                  Hang Yan and
                  Tao Gui and
                  Qi Zhang and
                  Xipeng Qiu and
                  Xuanjing Huang},
  title        = {Secrets of {RLHF} in Large Language Models Part {I:} {PPO}},
  journal      = {CoRR},
  volume       = {abs/2307.04964},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2307.04964},
  doi          = {10.48550/ARXIV.2307.04964},
  eprinttype    = {arXiv},
  eprint       = {2307.04964},
  timestamp    = {Wed, 14 Aug 2024 08:21:24 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2307-04964.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}
a service of  Schloss Dagstuhl - Leibniz Center for Informatics