EasyDeepLearn

A stakeholder wants the model to 'know our internal docs'. Do you fine-tune or build RAG?

medium

Answer

  • RAG, in almost every case.
  • Fine-tuning teaches style, format and task behaviour; it is a poor way to install facts, because the knowledge is baked in at training time and cannot be updated, cited or revoked.
  • RAG keeps documents in a store you can re-index nightly, lets you show sources so the answer is auditable, and handles access control because you can filter retrieval by permission.
  • Fine-tuning becomes the right answer when you need a specific output schema, a domain tone, or lower latency from a smaller model.
  • The two combine well: fine-tune for behaviour, retrieve for facts.
Check yourself — multiple choice
  • Always fine-tune
  • RAG for facts — updatable, citable, permission-filterable; fine-tune for format, tone and latency, and combine them
  • Neither works
  • Fine-tuning is cheaper for facts

Facts belong in retrieval; fine-tuning shapes behaviour and format.

#rag#fine-tuning

Practise LLMs & GenAI

214 interview questions in this topic.

Related questions