What is LLM fine-tuning?
Fine-tuning is the process of taking a pretrained language model and continuing its training on a smaller, domain-specific dataset to specialize the model for a task or style. It bakes knowledge into the model weights, in contrast to RAG which keeps the knowledge in an external database.
When to fine-tune
Fine-tune when you need consistent style or format that prompting cannot reliably produce, or when you have a task-specific dataset that improves performance over what the base model offers. Fine-tune sparingly: the operational overhead is significant and updates require a fresh training run.
When not to fine-tune
For frequently changing business facts, retrieval keeps the source material separate and easier to update. Fine-tuning changes model behavior or knowledge through training; it does not replace permission checks, source validation or ongoing evaluation.
Cost shape
Training cost depends on the model, dataset, method and hardware. Adapter methods can reduce the resources required compared with updating every model parameter. Compare measured quality and operating cost before adopting either approach.
See it working on message.com.
Unified inbox, grounded AI, flat pricing. 7-day free trial for chat and tickets. Credit card required.
Start free trial →