Training language models to follow instructions with human feedback

2022 article ouyang2022 ○ Not yet verified

Authors

Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray

Venue

Advances in Neural Information Processing Systems

BibTeX

Local Entry

@article{ouyang2022,
  title = {Training language models to follow instructions with human feedback},
  author = {Long Ouyang and Jeffrey Wu and Xu Jiang and Diogo Almeida and Carroll Wainwright and Pamela Mishkin and Chong Zhang and Sandhini Agarwal and Katarina Slama and Alex Ray},
  year = {2022},
  journal = {Advances in Neural Information Processing Systems},
  pages = {27730--27744},
  volume = {35}
}

From AUTO:S2

@article{ouyang2022,
  title = {Training language models to follow instructions with human feedback},
  author = {Long Ouyang and Jeff Wu and Xu Jiang and Diogo Almeida and Carroll L. Wainwright and Pamela Mishkin and Chong Zhang and Sandhini Agarwal and Katarina Slama and Alex Ray and John Schulman and Jacob Hilton and Fraser Kelton and Luke E. Miller and Maddie Simens and Amanda Askell and Peter Welinder and P. Christiano and Jan Leike and Ryan J. Lowe},
  year = {2022},
  journal = {Neural Information Processing Systems}
}