@article{thecapacityformoralselfcorrectionin,
  title = {The Capacity for Moral Self-Correction in Large Language Models},
  author = {Deep Ganguli and Amanda Askell and Nicholas Schiefer and Thomas I. Liao and Kamilė Lukošiūtė and Anna Chen and Anna Goldie and Azalia Mirhoseini and Catherine Olsson and Danny Hernandez and Dawn Drain and Dustin Li and Eli Tran-Johnson and Ethan Perez and Jackson Kernion and Jamie Kerr and Jared Mueller and Joshua Landau and Kamal Ndousse and Karina Nguyen and Liane Lovitt and Michael Sellitto and Nelson Elhage and Noemi Mercado and Nova DasSarma and Oliver Rausch and Robert Lasenby and Robin Larson and Sam Ringer and Sandipan Kundu and Saurav Kadavath and Scott Johnston and Shauna Kravec and Sheer El Showk and Tamera Lanham and Timothy Telleen-Lawton and Tom Henighan and Tristan Hume and Yuntao Bai and Zac Hatfield-Dodds and Ben Mann and Dario Amodei and Nicholas Joseph and Sam McCandlish and Tom Brown and Christopher Olah and Jack Clark and Samuel R. Bowman and Jared Kaplan},
  year = {2023},
  eprint = {2302.07459},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2302.07459v2},
}