BibTeX record journals/corr/abs-2401-06080

• > Home > journals/corr/abs-2401-06080

@article{DBLP:journals/corr/abs-2401-06080,
  author       = {Binghai Wang and
                  Rui Zheng and
                  Lu Chen and
                  Yan Liu and
                  Shihan Dou and
                  Caishuang Huang and
                  Wei Shen and
                  Senjie Jin and
                  Enyu Zhou and
                  Chenyu Shi and
                  Songyang Gao and
                  Nuo Xu and
                  Yuhao Zhou and
                  Xiaoran Fan and
                  Zhiheng Xi and
                  Jun Zhao and
                  Xiao Wang and
                  Tao Ji and
                  Hang Yan and
                  Lixing Shen and
                  Zhan Chen and
                  Tao Gui and
                  Qi Zhang and
                  Xipeng Qiu and
                  Xuanjing Huang and
                  Zuxuan Wu and
                  Yu{-}Gang Jiang},
  title        = {Secrets of {RLHF} in Large Language Models Part {II:} Reward Modeling},
  journal      = {CoRR},
  volume       = {abs/2401.06080},
  year         = {2024},
  url          = {https://doi.org/10.48550/arXiv.2401.06080},
  doi          = {10.48550/ARXIV.2401.06080},
  eprinttype    = {arXiv},
  eprint       = {2401.06080},
  timestamp    = {Wed, 14 Aug 2024 07:58:34 +0200},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2401-06080.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}