Constitutional AI: Harmlessness from AI feedback
Authors
Venue
arXiv preprint arXiv:2212.08073
BibTeX
Local Entry
@article{bai2022,
title = {Constitutional AI: Harmlessness from AI feedback},
author = {Yuntao Bai and Saurav Kadavath and Sandipan Kundu and Amanda Askell and Jackson Kernion and Andy Jones and Anna Chen and Anna Goldie and Azalia Mirhoseini and Cameron McKinnon},
year = {2022},
journal = {arXiv preprint arXiv:2212.08073}
} From AUTO:DBLP
@article{bai2022,
author = {Yuntao Bai and
Saurav Kadavath and
Sandipan Kundu and
Amanda Askell and
Jackson Kernion and
Andy Jones and
Anna Chen and
Anna Goldie and
Azalia Mirhoseini and
Cameron McKinnon and
Carol Chen and
Catherine Olsson and
Christopher Olah and
Danny Hernandez and
Dawn Drain and
Deep Ganguli and
Dustin Li and
Eli Tran{-}Johnson and
Ethan Perez and
Jamie Kerr and
Jared Mueller and
Jeffrey Ladish and
Joshua Landau and
Kamal Ndousse and
Kamile Lukosiute and
Liane Lovitt and
Michael Sellitto and
Nelson Elhage and
Nicholas Schiefer and
Noem{\'{\i}} Mercado and
Nova DasSarma and
Robert Lasenby and
Robin Larson and
Sam Ringer and
Scott Johnston and
Shauna Kravec and
Sheer El Showk and
Stanislav Fort and
Tamera Lanham and
Timothy Telleen{-}Lawton and
Tom Conerly and
Tom Henighan and
Tristan Hume and
Samuel R. Bowman and
Zac Hatfield{-}Dodds and
Ben Mann and
Dario Amodei and
Nicholas Joseph and
Sam McCandlish and
Tom Brown and
Jared Kaplan},
title = {Constitutional {AI:} Harmlessness from {AI} Feedback},
journal = {CoRR},
volume = {abs/2212.08073},
year = {2022},
url = {https://doi.org/10.48550/arXiv.2212.08073},
doi = {10.48550/ARXIV.2212.08073},
eprinttype = {arXiv},
eprint = {2212.08073},
timestamp = {Mon, 02 Jan 2023 15:09:55 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2212-08073.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}