HH-RLHF dataset

The HH-RLHF dataset is used to evaluate the performance of the proposed Compositional Preference Models (CPMs).

Data and Resources

Cite this as

Yuntao Bai, Andy Jones, Kamal Ndousse, Amanda Askell, Anna Chen, Nova DasSarma, Dawn Drain, Stanislav Fort, Deep Ganguli, Tom Henighan, et al. (2024). Dataset: HH-RLHF dataset. https://doi.org/10.57702/btkkm32x

DOI retrieved: December 2, 2024

Additional Info

Field Value
Created December 2, 2024
Last update December 2, 2024
Defined In https://doi.org/10.48550/arXiv.2401.13136
Author Yuntao Bai
More Authors
Andy Jones
Kamal Ndousse
Amanda Askell
Anna Chen
Nova DasSarma
Dawn Drain
Stanislav Fort
Deep Ganguli
Tom Henighan
et al.
Homepage https://huggingface.co/datasets/Bai-etal-2022-HH-RLHF