rAnked FineTuning
both large language models and diffusion models.
selects the high-quality samples, discarding those that exhibit undesired behavior, and subsequently enhancing the model by fine-tuning on these filtered samples
RAFT
Creator
Creator
Seonglae ChoCreated
Created
2023 Sep 9 17:12Editor
Editor
Seonglae ChoEdited
Edited
2023 Sep 9 17:17Refs
Refs