Record
- Authors
- Bai, Y.; Jones, A.; Ndousse, K.; Askell, A.; Chen, A.; DasSarma, N.; et al.
- Year
- 2022
- Title
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- Published in
- arXiv
- Type
- Preprint
- DOI
- 10.48550/arxiv.2204.05862
- arXiv
- arXiv:2204.05862
- Links
- https://arxiv.org/abs/2204.05862
https://www.anthropic.com/research/training-a-helpful-and-harmless-assistant-with-reinforcement-learning-from-human-feedback - Our note
- Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback
- Verification
- verified: its identifier resolves to a record with the same title and author (checked against OpenAlex, 2026-11-14).
Identifiers found: OpenAlex W4223908421 · DOI 10.48550/arxiv.2204.05862 · arXiv:2204.05862 - From the lookup
- doi (the pages' own wording is under "As cited" below)
- Id
bai-2022-training-helpful-harmless-assistant-reinforcement-learning
Cited on
- A General Language Assistant as a Laboratory for Alignment read status: not stated
- Constitutional AI: Harmlessness from AI Feedback read status: not stated
- Discovering Language Model Behaviors with Model-Written Evaluations 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
- 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 3 forms.
-
Bai, Y., Jones, A., Ndousse, K., Askell, A., Chen, A., DasSarma, N., et al. (2022). Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback. arXiv:2204.05862.on A General Language Assistant as a Laboratory for Alignment, Constitutional AI: Harmlessness from AI Feedback, Language Models (Mostly) Know What They Know, Discovering Language Model Behaviors with Model-Written Evaluations, Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned, Towards Understanding Sycophancy in Language Models
-
Bai, Y., Jones, A., Ndousse, K., Askell, A., Chen, A., DasSarma, N., Drain, D., Fort, S., Ganguli, D., Henighan, T., Joseph, N., Kadavath, S., Kernion, J., Conerly, T., El-Showk, S., Elhage, N., Hatfield-Dodds, Z., Hernandez, D., Hume, T., Johnston, S., Kravec, S., Lovitt, L., Nanda, N., Olsson, C., Amodei, D., Brown, T., Clark, J., McCandlish, S., Olah, C., Mann, B., and Kaplan, J. (2022a). Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback. arXiv:2204.05862v1, 12 April 2022. Anthropic. https://arxiv.org/abs/2204.05862. Anthropic page: https://www.anthropic.com/research/training-a-helpful-and-harmless-assistant-with-reinforcement-learning-from-human-feedback
-
Bai, Y., Jones, A., Ndousse, K., Askell, A., Chen, A., DasSarma, N., et al. (2022a). Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback. arXiv:2204.05862.
BibLaTeX
@misc{bai-2022-training-helpful-harmless-assistant-reinforcement-learning,
author = {Bai, Y. and Jones, A. and Ndousse, K. and Askell, A. and Chen, A. and DasSarma, N. and others},
title = {{Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback}},
date = {2022},
doi = {10.48550/arxiv.2204.05862},
eprint = {2204.05862},
eprinttype = {arxiv},
url = {https://www.anthropic.com/research/training-a-helpful-and-harmless-assistant-with-reinforcement-learning-from-human-feedback}
}