Record
- Authors
- Ganguli, D.; Lovitt, L.; Kernion, J.; Askell, A.; Bai, Y.; Kadavath, S.; et al.
- Year
- 2022
- Title
- Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
- Published in
- arXiv
- Type
- Preprint
- DOI
- 10.48550/arxiv.2209.07858
- arXiv
- arXiv:2209.07858
- Links
- https://arxiv.org/abs/2209.07858
https://github.com/anthropics/hh-rlhf
https://www.anthropic.com/research/red-teaming-language-models-to-reduce-harms-methods-scaling-behaviors-and-lessons-learned - Our note
- Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned
- Verification
- verified: its identifier resolves to a record with the same title and author (checked against OpenAlex, 2026-11-14).
Identifiers found: OpenAlex W4296413526 · DOI 10.48550/arxiv.2209.07858 · arXiv:2209.07858 - From the lookup
- doi (the pages' own wording is under "As cited" below)
- Id
ganguli-2022-red-teaming-language-models-reduce-harms
Cited on
- Forecasting rare language model behaviors read status: not stated
- Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned read status: not stated
As cited
The pages cite this work in 2 forms.
-
Ganguli, D., Lovitt, L., Kernion, J., Askell, A., Bai, Y., Kadavath, S., Mann, B., Perez, E., Schiefer, N., Ndousse, K., Jones, A., Bowman, S., et al. (2022). Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned. Anthropic. arXiv:2209.07858v2, revised 22 November 2022 (v1 submitted 23 August 2022). https://arxiv.org/abs/2209.07858. Anthropic page: https://www.anthropic.com/research/red-teaming-language-models-to-reduce-harms-methods-scaling-behaviors-and-lessons-learned. Dataset: https://github.com/anthropics/hh-rlhf
-
Ganguli, D., Lovitt, L., Kernion, J., Askell, A., Bai, Y., Kadavath, S., et al. (2022). Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned. arXiv:2209.07858.
BibLaTeX
@misc{ganguli-2022-red-teaming-language-models-reduce-harms,
author = {Ganguli, D. and Lovitt, L. and Kernion, J. and Askell, A. and Bai, Y. and Kadavath, S. and others},
title = {{Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned}},
date = {2022},
doi = {10.48550/arxiv.2209.07858},
eprint = {2209.07858},
eprinttype = {arxiv},
url = {https://github.com/anthropics/hh-rlhf}
}