Self-Supervised Alignment with Mutual Information

The dataset is used for training a language model to follow behavioral principles without the use of preference labels, demonstrations, or human oversight.

Data and Resources

Cite this as

Jan-Philipp Fränken, Eric Zelikman, Rafael Rafailov, Kanishk Gandhi, Tobias Gerstenberg, Noah D. Goodman (2024). Dataset: Self-Supervised Alignment with Mutual Information. https://doi.org/10.57702/eafwuidh

DOI retrieved: December 3, 2024

Additional Info

Field Value
Created December 3, 2024
Last update December 3, 2024
Author Jan-Philipp Fränken
More Authors
Eric Zelikman
Rafael Rafailov
Kanishk Gandhi
Tobias Gerstenberg
Noah D. Goodman
Homepage https://github.com/janphilippfranken/sami