BibTeX record journals/corr/abs-2310-05199

• > Home > journals/corr/abs-2310-05199

@article{DBLP:journals/corr/abs-2310-05199,
  author       = {Wei Shen and
                  Rui Zheng and
                  WenYu Zhan and
                  Jun Zhao and
                  Shihan Dou and
                  Tao Gui and
                  Qi Zhang and
                  Xuanjing Huang},
  title        = {Loose lips sink ships: Mitigating Length Bias in Reinforcement Learning
                  from Human Feedback},
  journal      = {CoRR},
  volume       = {abs/2310.05199},
  year         = {2023},
  url          = {https://doi.org/10.48550/arXiv.2310.05199},
  doi          = {10.48550/ARXIV.2310.05199},
  eprinttype    = {arXiv},
  eprint       = {2310.05199},
  timestamp    = {Fri, 22 Mar 2024 10:55:02 +0100},
  biburl       = {https://dblp.org/rec/journals/corr/abs-2310-05199.bib},
  bibsource    = {dblp computer science bibliography, https://dblp.org}
}