You're currently viewing an old version of this dataset. To see the current version, click here.

ETHICS benchmark

The ETHICS benchmark is a dataset for evaluating the ethics of language models.

Data and Resources

Cite this as

Hendrycks et al. (2024). Dataset: ETHICS benchmark. https://doi.org/10.57702/ali0ssck

DOI retrieved: December 16, 2024

Additional Info

Field Value
Created December 16, 2024
Last update December 16, 2024
Defined In https://doi.org/10.48550/arXiv.2404.18870
Author Hendrycks et al.
Homepage https://arxiv.org/abs/2008.02275