Tom Conerly
According to our database1,
Tom Conerly
authored at least 8 papers
in 2022.
Collaborative distances:
Collaborative distances:
Timeline
2022
0
1
2
3
4
5
6
7
8
9
7
1
Legend:
Book In proceedings Article PhD thesis Dataset OtherLinks
On csauthors.net:
Bibliography
2022
Red Teaming Language Models to Reduce Harms: Methods, Scaling Behaviors, and Lessons Learned.
CoRR, 2022
Training a Helpful and Harmless Assistant with Reinforcement Learning from Human Feedback.
CoRR, 2022
Proceedings of the FAccT '22: 2022 ACM Conference on Fairness, Accountability, and Transparency, Seoul, Republic of Korea, June 21, 2022