The stage after pretraining that shapes a model’s behavior and preferences.
Post-training is finishing school for an AI. It already read the library. Now it learns not to interrupt Grandma.
It tunes safety and preferences before an assistant goes live. You feel it when a chatbot follows instructions and stays polite.
Pretraining
Pretraining teaches broad knowledge first. Post-training then shapes behavior and preferences.
Fine-tuning
Fine-tuning is one common tool used during post-training.
Instruction Tuning
Instruction Tuning uses examples to teach the model to follow requests.
RLHF
RLHF uses human feedback to make answers fit human preferences.