상황
A deployed language model collects user prompts and generates candidate responses; users rank responses to create preference data used to train a reward model and update the policy.
이 도면에 담긴 내용
그 이면의 의사결정을 읽어 보세요.
01
User ranks responses or session discarded
02
Policy converged or continue training loop
Use for RLHF pipelines, chat model alignment, or any interactive preference-based fine-tuning flow.