Seonglae ChoSupervised Fine-Tuning
SFT rarely alters the underlying model capabilities which means practitioners can unintentionally remove a model’s safety wrapper by merely fine-tuning it on a superficially unrelated task
OOD generalization is crucial given the wide range of real-world scenarios in which these models are being used, while output diversity refers to the model’s ability to generate varied outputs and is important for a variety of use cases
RLHF generalizes better than SFT to new inputs, particularly as the distribution shift between train and test becomes larger. However, RLHF significantly reduces output diversity compared to SFT across a variety of measures, implying a tradeoff in current LLM fine-tuning methods between generalization and diversity.
