# Fine-Tuning

> Fine-tuning is the further training of a pretrained model on a smaller, task- or domain-specific dataset so that its weights adapt to that task or domain.

- Identifier: PTL-0105
- Category: Foundations
- Canonical URL: https://protologue.com/t/fine-tuning/
- Also known as: model fine-tuning, transfer learning
- Introduced: 2018

## Description

Fine-tuning complements prompting. Prompting changes only the input, while fine-tuning changes the model, which can teach a consistent format, style, or specialized skill that is hard to obtain from instructions alone, at the cost of training data, compute, and a separate model to maintain. Parameter-efficient methods such as LoRA update only a small number of added weights, and instruction tuning is the fine-tuning step that turns a base model into an assistant.

## Narrower terms

- [Knowledge Distillation](https://protologue.com/t/knowledge-distillation/)

## Related terms

- [Base Model](https://protologue.com/t/base-model/)
- [Instruction Tuning](https://protologue.com/t/instruction-tuning/)
- [Low-Rank Adaptation](https://protologue.com/t/low-rank-adaptation/)
- [Prompt Tuning](https://protologue.com/t/prompt-tuning/)

## Comparisons

- [Fine-Tuning vs Retrieval-Augmented Generation](https://protologue.com/compare/rag-vs-fine-tuning/)
- [Fine-Tuning vs Low-Rank Adaptation](https://protologue.com/compare/lora-vs-fine-tuning/)

## Sources

- Howard and Ruder (2018). Universal Language Model Fine-tuning for Text Classification. https://arxiv.org/abs/1801.06146
- Hu et al. (2021). LoRA: Low-Rank Adaptation of Large Language Models. https://arxiv.org/abs/2106.09685

## Cite this entry

Protologue. (2026). Fine-Tuning. In Protologue: A Taxonomy of Prompting and LLM Techniques (v1.4.0, PTL-0105). https://protologue.com/t/fine-tuning/

License: CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)