Skip to content

Retrieval, Fine-Tuning, or Both?

This choice is made badly more often than any other in custom LLM projects, usually because fine-tuning sounds more impressive. Twelve questions about your actual requirements will point to the right architecture — which for most organisations is not the one they assumed.

A higher score points towards retrieval; a lower score towards fine-tuning. Scores in the middle usually mean retrieval first, with fine-tuning considered later if a specific gap remains.

RAG or Fine-Tuning?

Higher scores point to retrieval. Lower scores point to fine-tuning.

0 of 12 answered0%
1.How often does the underlying information change?
2.If a fact changes, how quickly must the system reflect it?
3.How large is the body of knowledge involved?
4.What does the system primarily need to do?
5.How important is a consistent tone and structure in every response?
6.Have you tried achieving the desired behaviour with prompting?
7.Do users need to see the source of an answer?
8.Does the answer need to be auditable for compliance?
9.Must different users see different information based on permissions?
10.Do you have labelled examples of ideal input and output?
11.Can subject-matter experts commit months to producing training data?
12.How quickly do you need something working?
Answer all 12 questions to see your score and a tailored recommendation.

A guide to structure the architecture conversation, not a substitute for technical assessment of your specific data and requirements.

What Each Approach Actually Does

The distinction is often described as knowledge versus behaviour, and that framing holds up well in practice. Confusing the two is what produces expensive projects that answer the wrong problem.

Retrieval gives the model knowledge

Retrieval-augmented generation fetches relevant documents at query time and passes them to the model as context. The model does not learn your information — it reads it each time — which means updating your knowledge is as simple as updating a document.

Fine-tuning changes behaviour

Fine-tuning adjusts the model’s weights using examples of the input and output you want. It is effective for teaching a consistent style, format or task pattern, and ineffective as a way of teaching facts, which is the most common misuse.

Both together is legitimate but rarely first

Mature systems sometimes fine-tune for consistent output format and use retrieval for current information. That combination is real, but attempting it initially means debugging two variables at once. Retrieval first is almost always the correct starting point.

The Four Things That Decide It

Twelve questions across four dimensions. Data volatility carries the most weight, because it is the factor most likely to make fine-tuning the wrong answer outright.

1

Data volatility

How often the underlying information changes. Frequently changing knowledge strongly favours retrieval, because re-training on every change is impractical.

2

Output requirements

Whether you need factual answers grounded in documents, or consistent behaviour, tone and structure across every response.

3

Traceability

Whether users need to see where an answer came from. Citation is straightforward with retrieval and effectively impossible with fine-tuning alone.

4

Resources and data availability

Whether you have thousands of high-quality training examples and the budget to produce and maintain them.

The Four Misconceptions That Cost the Most

These come up in nearly every architecture conversation, and each one has led organisations to spend heavily on the wrong approach.

"We will fine-tune the model on our documents"

This is the single most expensive misconception in the field. Fine-tuning on a document corpus teaches the model to imitate the style of those documents, not to recall their contents reliably. Ask it a specific factual question and it will produce something that reads correctly and may be entirely invented.

  • Fine-tuning teaches patterns and style, not reliable factual recall
  • Facts learned in training cannot be cited or verified
  • Updating a single fact requires re-training the entire model
  • Retrieval is the correct approach for document-grounded answers

"Fine-tuning will be cheaper than paying for context"

Occasionally true at very high query volumes, but the comparison usually omits the cost of producing training data, the engineering effort, and re-training whenever the model provider deprecates a version. Reducing retrieved context is a far cheaper way to cut token spend.

  • Training data preparation is usually the dominant cost
  • Model deprecation forces periodic re-training you must budget for
  • Context reduction achieves similar savings for a fraction of the effort
  • Compare total cost of ownership, not per-query token cost alone

"Fine-tuning will make it more accurate"

It makes output more consistent, which is not the same thing. If the model is producing factually wrong answers, that is usually a retrieval problem — it was not given the right information — and fine-tuning will make the wrong answers more consistently formatted rather than correct.

  • Diagnose whether failures are retrieval failures or generation failures
  • Retrieval failures are fixed by better retrieval, not by training
  • Fine-tuning improves format and tone consistency reliably
  • Measure both retrieval quality and answer quality separately

"We need a fine-tuned model to sound like us"

Sometimes true, but prompt engineering with good examples achieves most of this for a tiny fraction of the cost and effort. Try the cheap approach thoroughly before committing to the expensive one — the gap is frequently smaller than expected.

  • Try few-shot prompting with strong examples first
  • A detailed system prompt handles most tone requirements
  • Fine-tune only if prompting demonstrably falls short after real effort
  • Measure the difference rather than assuming it

Next Steps

LLM Cost Calculator

Architecture drives cost. Model what your chosen approach will run to.

Model the cost

RAG Architecture in Australia

How retrieval systems are built and deployed for Australian organisations.

Read the guide

Private LLM Readiness Assessment

Check your data and governance foundations before building either.

Assess readiness

Frequently Asked Questions

Not Sure the Answer Fits?

Tell us your use case and we will tell you which architecture we would choose and why — including when the honest answer is that you do not need a custom model at all.