Compare RAG and fine-tuning. When would you use each?

For AI / LLM Engineer ML Engineer Data Scientist

The short answer

RAG injects external knowledge at inference time and is best when information changes often, must be cited, or is too large to bake into weights. Fine-tuning changes model behavior, style, or format and is best for teaching new skills or domain tone; the two are complementary and often combined.

How to think about it

Learn it properly Fine-tune vs RAG: the decision

Keep practising

When should you use RAG vs fine-tuning vs a long-context model? What is Retrieval-Augmented Generation (RAG) and why is it used? What are chunking strategies in RAG, and how do you choose chunk size? What is Retrieval-Augmented Generation (RAG) and how does a basic RAG pipeline work? Your RAG system is hallucinating even though the correct context was retrieved. How do you debug it?

All NLP & LLMs questions

Explore further

RAG evaluations Advanced RAG RAG basics

Fine-Tuning RAG LoRA Inference scikit-learn