When to fine-tune rather than prompt or retrieve, LoRA and parameter-efficient methods, dataset curation, and evaluating whether it helped.
4 questions in Generative AI & Large Language Models.
Use RAG for the knowledge, because articles change weekly and retrieval lets you edit, withdraw and cite them without retraining. Fine-tune only for behaviour retrieval cannot fix, such as tone, escalation judgement or reply format, and decide by auditing real failures and evaluating each fix on its own slice.
Ask what is missing. If the answer changes when your documents change, you need retrieval; if the model knows enough but will not behave, format or specialise the way you need, you fine-tune. Prompting comes first either way because it costs an afternoon and tells you which of the other two you actually need.
Compare it against a genuinely strong prompted baseline on a held-out set drawn from real traffic, using the task metric your product cares about, and run a broad regression set alongside to catch capability lost elsewhere. Falling training loss is evidence that training worked, not that the product improved.
LoRA freezes the base weights and trains a small low-rank update added to chosen projections, so you train a fraction of the parameters and can swap adapters per use case. It reshapes behaviour and format readily, installs facts poorly, and rank is the capacity dial with overfitting beyond it. It also connects PEFT to the point an interviewer is testing.