What fine-tuning actually changes

There’s a common misconception that fine-tuning is how you “add knowledge” to a language model. Usually it isn’t. Fine-tuning is much better at changing behaviour — format, tone, tool use, how the model decides what to do — than at reliably injecting new facts.

Behaviour moves easily

If you want a model to always answer in a particular JSON shape, prefer a house style, or reach for a specific tool when it sees a certain kind of request, a few hundred well-chosen examples go a long way. You’re not teaching the model anything it can’t already express; you’re shifting which of its existing behaviours it defaults to.

Facts move stubbornly

Trying to teach durable factual knowledge through fine-tuning is fragile. The model may repeat a fact it saw during training, but it will also happily contradict it, and you have no clean way to update or retract it later. Retrieval — putting the fact in the prompt at inference time — is almost always the better tool for that job.

A rule of thumb

Ask whether the thing you want is a skill or a fact.

• Skill (do this task, in this shape, with these tools) → fine-tuning fits.
• Fact (this specific, changeable piece of information) → retrieval fits.

Most real systems want both: retrieval for what’s true right now, fine-tuning for how the model should behave when it answers.