What is Fine-tuning?
Training an existing model a little more on your own examples so it behaves in the way you want.
In plain English
The model’s internal weights are adjusted using a smaller, targeted dataset. It is useful for a consistent style, format or specialist behaviour. It is usually a poor way to add fast-changing facts, because the knowledge is fixed at training time. It costs more effort than prompting or RAG, so try those first.
Example
Training a model on thousands of approved customer replies so its tone matches your brand.
Easy to confuse with
- Retrieval-augmented generation (RAG): Fine-tuning changes the model. RAG adds documents to each request.
Where you will meet it
This idea belongs to the subject area of these practice tests. We do not publish or predict real exam questions.
- AWS AIF-C01 practice tests
- NVIDIA NCA-GENL practice tests
- Databricks GenAI Engineer Associate practice tests
- Google Cloud Generative AI Leader practice tests
Related terms
- Retrieval-augmented generation (RAG): Letting a model look up relevant documents first and answer using them.
- Prompt engineering: Writing instructions and context so an AI model gives a more useful answer.
- Overfitting: When a model learns its training data too closely and does badly on new data.
Test yourself
Practice tests with an explanation for every answer option, so each mistake teaches you something.
Browse practice testsAll glossary termsWritten and checked by the Be Ready Education team, last reviewed 2 November 2026. General study information, not professional advice. Providers change names and rules, so confirm details on the official documentation. Not affiliated with, endorsed by or sponsored by any certification vendor or exam body. Certification names, exam codes and product names are trademarks of their respective owners and are used only to identify the exam a practice product prepares for. Our questions are original and are not actual exam questions.