• RLHF — Reinforcement learning from human feedback — training a model to prefer answers humans rate as better, which turns a raw text predictor into a usable assistant.

It stripped most of the machinery out of preference training: no separate reward model, no RL loop, just a classification loss that reaches comparable quality and is stable enough to run without a research team. Most open-model post-training you see now is DPO or a descendant.

• articleGSPO: Towards Scalable Reinforcement Learning for Language ModelsQwen Team
• articleTraining language models to follow instructions with human feedbackLong Ouyang et al.
• videoWhat's Next After RLHF? — Diogo Almeida, TypeSafe AIAI Engineer

Sign in to comment.

Loading comments…