Home
GLOSSARY
Fine-Tuning

Fine-Tuning

IN ONE LINE

Fine-tuning is further training of an existing AI model on your own examples so it consistently follows a specific style, format or task.

What is Fine-Tuning?

Fine-tuning takes a pre-trained model and trains it further on a curated dataset of inputs and ideal outputs. The model's behaviour shifts toward those examples, for example always replying in a certain format or classifying items the way your team does.

Why it matters

It can improve consistency, shorten prompts and lower cost on narrow, repetitive tasks. But it is often chosen too early, when better prompting or RAG would solve the problem faster and cheaper.

How it works

Teams collect and clean high-quality examples, hold some back for testing, train the model through a provider's fine-tuning service or on open models, then compare it against the base model with evals before switching.

Common mistakes

  • Fine-tuning to add knowledge, which RAG usually handles better.
  • Training on too few or inconsistent examples.
  • No eval comparison against the base model.
  • Forgetting the fine-tuned model needs maintaining when base models improve.

How Dev Monks approaches it

Dev Monks advises on whether fine-tuning is worth it for your use case, and usually starts with prompting and RAG, moving to fine-tuning only when evals show a clear benefit.

FAQs

Is fine-tuning expensive?

Training can be affordable, but data preparation, evaluation and maintenance are the real costs.

Can fine-tuning stop hallucinations?

Not reliably. Grounding answers with RAG and evals is more effective.

Related terms

Need help with this? See our AI Consulting service.