AI engineering glossary · LLM training alignment
What is prompt tuning?
Prompt tuning (also called Soft prompt tuning): A parameter-efficient method that learns a short sequence of continuous embedding vectors placed at the input of a frozen model, so the task is encoded in the learned 'soft prompt' rather than in weights or hand-written text.
Prompt tuning: an example
100 learned soft-prompt vectors are prepended to every input for a topic-classification task.
Related terms
- Prefix tuning
- Parameter-efficient fine-tuning
- Soft prompt
More LLM training alignment terms
- Proximal policy optimisation
- QLoRA
- Rank (LoRA)
- Reasoning model
- Reinforcement learning from AI feedback
- Reinforcement learning from human feedback
- Reinforcement learning with verifiable rewards
- Rejection sampling fine-tuning
Where you learn it
Prompt tuning is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.