---
title: Fine-Tuning — AI Glossary
description: 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.
canonical: https://prompeteer.ai/glossary/fine-tuning
---

# 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

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.

## Sources

- [OpenAI — Fine-tuning guide](https://platform.openai.com/docs/guides/fine-tuning)
- [Howard & Ruder (2018), Universal Language Model Fine-tuning (ULMFiT)](https://arxiv.org/abs/1801.06146)

## Related terms

- [lora](https://prompeteer.ai/glossary/lora)
- [rlhf](https://prompeteer.ai/glossary/rlhf)
- [distillation](https://prompeteer.ai/glossary/distillation)
- [quantization](https://prompeteer.ai/glossary/quantization)