Activity (Process)

Typical Sequence of LLM Alignment Methods

After a Large Language Model completes its initial pre-training stage, alignment is typically achieved by applying three methods in a specific sequence. First, Supervised Fine-Tuning (SFT) is performed to adapt the model to specific instructions. Second, Reinforcement Learning from Human Feedback (RLHF) is utilized to align the model with complex human preferences and values. Finally, during the inference stage, prompting techniques are employed to dynamically guide the model's behavior for specific tasks.

0

1

Updated 2026-04-30

Contributors are:

Who are from:

Tags

Foundations of Large Language Models

Ch.4 Alignment - Foundations of Large Language Models

Foundations of Large Language Models Course

Computing Sciences