Fine-Tuning

Fine-tuning adapts a pre-trained model to a specific task or style by continuing training on a smaller, curated dataset, updating the model's weights. Unlike prompting, which steers a frozen model at inference time, fine-tuning changes the model itself so the new behavior is baked in.

Definition

Fine-Tuning

A pre-trained model already encodes broad language and world knowledge. Fine-tuning takes that base and trains it further on labeled examples for a narrower objective — a domain vocabulary, an output format, or a task the base model handles inconsistently. It can improve reliability and reduce the prompt length needed to elicit desired behavior.

Full fine-tuning updates all parameters and is expensive; parameter-efficient methods such as LoRA update only a small set of added weights. Fine-tuning is most worthwhile when prompting and retrieval have been exhausted and there is enough high-quality task data to learn from.

Frequently asked questions

What is Fine-Tuning?

Fine-tuning adapts a pre-trained model to a specific task or style by continuing training on a smaller, curated dataset, updating the model's weights. Unlike prompting, which steers a frozen model at inference time, fine-tuning changes the model itself so the new behavior is baked in.

Sources

Related terms

← Full AI & prompt engineering glossary

Put Fine-Tuning to work with Prompeteer, the Agentic Contextual AI Platform →