# Fine-tuning

URL: https://www.onsomble.ai/tools/ai-glossary/fine-tuning

Published: 2026-03-15 00:00:00.000Z

The process of further training a pre-trained model on a smaller, task-specific dataset to improve its performance on that particular task or domain.

Category: Models & Platforms

## When to fine-tune

Fine-tuning makes sense when you need to teach a model a specific style, format, or domain vocabulary that prompt engineering alone can't capture. Common use cases include custom tone-of-voice, specialized classification, and structured output formatting.

## Fine-tuning vs. RAG

A common misconception is that fine-tuning teaches a model new facts. In practice, **RAG is better for knowledge** (it can be updated without retraining) while **fine-tuning is better for behavior** (teaching the model how to respond, not what to say).

## Techniques

-   **Full fine-tuning** — updates all model weights. Expensive but thorough.
-   **LoRA / QLoRA** — only trains small adapter layers. Much cheaper, often 90%+ of the quality.
-   **RLHF** — fine-tunes using human preference data to align model behavior.
-   **DPO** — Direct Preference Optimization, a simpler alternative to RLHF.

## Why it matters

Fine-tuning lets you customize foundation models for your exact use case. The rise of parameter-efficient methods like LoRA has made it accessible to teams without massive GPU budgets.

## Related terms

- [Large Language Model](https://www.onsomble.ai/tools/ai-glossary/large-language-model)
- [Retrieval-Augmented Generation](https://www.onsomble.ai/tools/ai-glossary/retrieval-augmented-generation)
- [Embeddings](https://www.onsomble.ai/tools/ai-glossary/embeddings)

## Related Radar topics

## Related articles

### [RAG vs Fine-Tuning: A Decision Framework for Real Projects](https://www.onsomble.ai/blog/rag-vs-fine-tuning-decision-framework)

RAG and fine-tuning solve different problems. Here's how to decide which one your project actually needs.

Rosh Jayawardena · Published 2025-12-25T12:00:00+00:00 · Updated 2026-08-02T12:12:41.52786+00:00 · 9 min
