Record
- Authors
- Bai, Y.; Kadavath, S.; Kundu, S.; Askell, A.; Kernion, J.; Jones, A.; et al.
- Year
- 2022
- Title
- Constitutional AI: Harmlessness from AI Feedback
- Published in
- arXiv
- Type
- Preprint
- DOI
- 10.48550/arxiv.2212.08073
- arXiv
- arXiv:2212.08073
- Links
- https://arxiv.org/abs/2212.08073
https://www.anthropic.com/research/constitutional-ai-harmlessness-from-ai-feedback - Our note
- Constitutional AI: Harmlessness from AI Feedback
- Verification
- verified: its identifier resolves to a record with the same title and author (checked against OpenAlex, 2026-11-14).
Identifiers found: OpenAlex W4311991106 · DOI 10.48550/arxiv.2212.08073 · arXiv:2212.08073 - From the lookup
- doi (the pages' own wording is under "As cited" below)
- Id
bai-2022-constitutional-ai-harmlessness-from-ai-feedback
Cited on
- A General Language Assistant as a Laboratory for Alignment read status: not stated
- Anthropic Research read status: not stated
- Challenges in evaluating AI systems read status: not stated
- Claude's Character read status: not stated
- Claude's Constitution read status: not stated
- Collective Constitutional AI: Aligning a Language Model with Public Input read status: not stated
- Constitutional AI: Harmlessness from AI Feedback read status: not stated
- Language Models (Mostly) Know What They Know read status: not stated
- Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned read status: not stated
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training read status: not stated
- Specific versus General Principles for Constitutional AI read status: not stated
- Sycophancy to Subterfuge: Investigating Reward Tampering in Language Models read status: not stated
- The Capacity for Moral Self-Correction in Large Language Models read status: not stated
- Towards Understanding Sycophancy in 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 7 forms.
-
Bai, Y., Kadavath, S., Kundu, S., Askell, A., Kernion, J., et al. (2022). Constitutional AI: Harmlessness from AI Feedback. arXiv:2212.08073.
-
Bai, Y., Kadavath, S., Kundu, S., Askell, A., Kernion, J., Jones, A., et al. (2022). Constitutional AI: Harmlessness from AI feedback. arXiv:2212.08073. https://arxiv.org/abs/2212.08073
-
Bai, Y., Kadavath, S., Kundu, S., Askell, A., Kernion, J., Jones, A., et al. (2022). Constitutional AI: Harmlessness from AI Feedback. arXiv:2212.08073.
-
Bai, Y., Kadavath, S., Kundu, S., Askell, A., Kernion, J., Jones, A., et al. (2022b). Constitutional AI: Harmlessness from AI Feedback. arXiv:2212.08073.
-
Bai, Y., Kadavath, S., Kundu, S., et al. (2022). Constitutional AI: Harmlessness from AI Feedback. arXiv:2212.08073.
-
Bai, Y., Kadavath, S., Kundu, S., Askell, A., Kernion, J., Jones, A., Chen, A., Goldie, A., Mirhoseini, A., McKinnon, C., et al. (2022). Constitutional AI: Harmlessness from AI Feedback. arXiv:2212.08073v1, submitted 15 December 2022. Anthropic. https://arxiv.org/abs/2212.08073. Anthropic page: https://www.anthropic.com/research/constitutional-ai-harmlessness-from-ai-feedback
-
Bai, Y., Kadavath, S., Kundu, S., et al. (2022). Constitutional AI: Harmlessness from AI Feedback. arXiv:2212.08073v1.
BibLaTeX
@misc{bai-2022-constitutional-ai-harmlessness-from-ai-feedback,
author = {Bai, Y. and Kadavath, S. and Kundu, S. and Askell, A. and Kernion, J. and Jones, A. and others},
title = {{Constitutional AI: Harmlessness from AI Feedback}},
date = {2022},
doi = {10.48550/arxiv.2212.08073},
eprint = {2212.08073},
eprinttype = {arxiv},
url = {https://www.anthropic.com/research/constitutional-ai-harmlessness-from-ai-feedback}
}