Fine-tuning
Continuing to train a pretrained model on a task-specific dataset to change its behavior, style, or domain knowledge. Techniques range from full fine-tuning (all weights) to parameter-efficient methods like LoRA and QLoRA that update only small adapter layers.
Related terms
- LoRA
Low-Rank Adaptation — a parameter-efficient fine-tuning technique that freezes the base model and trains small rank-decomposition matrices instead. Reduces fine-tuning cost by 10-100× and enables swapping many task-specific adapters over a single base model.
- RLHF
Reinforcement Learning from Human Feedback — a training method where human preferences over pairs of outputs are used to train a reward model, which in turn shapes the base LLM via RL (typically PPO or DPO). Central to aligning modern chat assistants.
- Retrieval-Augmented Generation (RAG)
A pattern where an LLM answers a query by first retrieving relevant documents from an external corpus (typically via a vector database or hybrid search) and injecting them into the prompt as grounding context. RAG addresses freshness and factual grounding without model retraining.
Related on this site
Where this fits
Fine-tuning is part of the AI Fundamentals vocabulary used in the Generative AI Maturity Framework. See the full glossary for the complete set of 149 defined terms, or take the free maturity assessment to see where your organisation stands.