AI engineering glossary · LLM training alignment
What is post-training?
Post-training: All the training stages applied after pretraining to make a base model useful and safe, typically supervised fine-tuning, preference optimisation, reinforcement learning and safety tuning. It uses far less compute than pretraining but strongly shapes how the model behaves with users.
Post-training: an example
After pretraining, a lab runs SFT on curated conversations, then preference tuning on ranked answers, then safety tuning; this whole sequence is post-training.
Related terms
More LLM training alignment terms
- Preference data
- Prefix tuning
- Pretraining
- Process reward model
- Prompt tuning
- Proximal policy optimisation
- QLoRA
- Rank (LoRA)
Where you learn it
Post-training is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.