The Capacity for Moral Self-Correction in Large Language Models

Record

Authors
Ganguli, D.; Askell, A.; Schiefer, N.; Liao, T. I.; Lukošiūtė, K.; et al.
Year
2023
Title
The Capacity for Moral Self-Correction in Large Language Models
Published in
arXiv
Type
Preprint
DOI
10.48550/arxiv.2302.07459
arXiv
arXiv:2302.07459
Links
https://arxiv.org/abs/2302.07459
https://www.anthropic.com/research/the-capacity-for-moral-self-correction-in-large-language-models
Our note
The Capacity for Moral Self-Correction in Large Language Models
Verification
verified: its identifier resolves to a record with the same title and author (checked against OpenAlex, 2026-11-14).
Identifiers found: OpenAlex W4321162379 · DOI 10.48550/arxiv.2302.07459 · arXiv:2302.07459
From the lookup
doi (the pages' own wording is under "As cited" below)
Id
ganguli-2023-capacity-moral-self-correction-large-language

Cited on

As cited

The pages cite this work in 2 forms.

BibLaTeX

@misc{ganguli-2023-capacity-moral-self-correction-large-language,
  author = {Ganguli, D. and Askell, A. and Schiefer, N. and Liao, T. I. and Lukošiūtė, K. and others},
  title = {{The Capacity for Moral Self-Correction in Large Language Models}},
  date = {2023},
  doi = {10.48550/arxiv.2302.07459},
  eprint = {2302.07459},
  eprinttype = {arxiv},
  url = {https://www.anthropic.com/research/the-capacity-for-moral-self-correction-in-large-language-models}
}

Download · JSON with CSL-JSON · the whole bibliography