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
- Constitutional AI: Harmlessness from AI Feedback read status: not stated
- Evaluating and Mitigating Discrimination in Language Model Decisions read status: not stated
- Specific versus General Principles for Constitutional AI read status: not stated
- The Capacity for Moral Self-Correction in Large Language Models read status: not stated
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback read status: not stated
As cited
The pages cite this work in 2 forms.
-
Ganguli, D., Askell, A., Schiefer, N., Liao, T. I., Lukošiūtė, K., et al. (2023). The Capacity for Moral Self-Correction in Large Language Models. arXiv:2302.07459.
-
Ganguli, D., Askell, A., Schiefer, N., Liao, T. I., Lukošiūtė, K., Chen, A., Goldie, A., Mirhoseini, A., Olsson, C., Hernandez, D., et al. (2023). The Capacity for Moral Self-Correction in Large Language Models. arXiv:2302.07459v2, 18 February 2023. Anthropic. https://arxiv.org/abs/2302.07459. Anthropic page: https://www.anthropic.com/research/the-capacity-for-moral-self-correction-in-large-language-models
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}
}