Skip to content
Sitebard AI
Machine Learning

Fine-Tuning

The process of further training a pre-trained model on a smaller, task-specific dataset to specialize its behavior.

By Sitebard TeamUpdated March 27, 2026

In plain English

Fine-tuning is taking a model that already knows a lot and giving it extra training on your own examples. This teaches it to do a specific job better, such as writing in your brand's voice.

Technical definition

Fine-tuning is a transfer-learning technique that continues training a pre-trained model on a smaller, task-specific labeled dataset, updating some or all of its parameters. Parameter-efficient methods such as LoRA adjust only a small subset of weights to reduce compute and storage costs.

Business use case

Companies fine-tune general-purpose models so outputs consistently match their domain terminology, tone, and formatting requirements. This is valuable for tasks like classifying support tickets or drafting documents in a regulated industry where precision and consistency matter.

Example

A law firm fine-tunes a language model on thousands of its past contracts so the model drafts new clauses using the firm's preferred legal wording.

Frequently asked questions

Fine-tuning adapts an already-trained model to a specific task or domain by training it further on a focused dataset, improving its accuracy and style for that use case.

Prompting changes a model's output by adjusting the instructions you give it, while fine-tuning changes the model's internal weights through additional training, producing more durable behavior changes.

Fine-tuning is worthwhile when prompting alone cannot achieve the consistency, tone, or domain accuracy you need, and you have enough high-quality labeled examples to train on.

Keep exploring

View all

Put AI intelligence to work in your business

Sitebard AI brings together the data, guides, and career intelligence you need to make confident AI decisions.