Fine-tuning starts from a pretrained model instead of learning every capability from the beginning. Training updates some or all model parameters using curated data, demonstrations, preferences, rewards, or another focused learning objective.
A successful fine-tune needs representative data, validation, preserved base capabilities, version tracking, and evaluation against the intended workflow. Poor data or excessive training can create overfitting, bias, regressions, or unwanted memorization.
ELI5
Fine-tuning continues training an existing AI model on additional examples so its stored weights better fit a task, field or preferred behavior. It starts from a model that already knows broad patterns instead of learning everything from zero.
For example, a company can fine-tune a model on reviewed examples of its support format. The change remains in the new model version, so teams need evaluations for improvement, regressions and overfitting rather than assuming more training always helps.
