liveBook · Manning

Adaptation technique

As explained in LLM Customization and Fine-Tuning

The specific method used to modify a base model, such as prompting, RAG, LoRA, fine-tuning, distillation, or alignment.

An adaptation technique is the method used to tailor a language model to a task. Options form a continuum from prompting and retrieval-augmented generation (RAG) through LoRA and full supervised fine-tuning (SFT) to distillation and alignment. section 1.11

Choose a technique by matching the task to the method, rather than assuming heavier adaptation is better.

  • Ask whether fine-tuning is needed, how much data is available, whether to use an open-source model or frontier API, and whether the goal is fine-tuning, distillation, or alignment. section 1.11
  • Treat technique choice as one stage in a lifecycle: base model and curated data, adaptation, evaluation, deployment and monitoring, then feedback to data curation. section 1.11
  • Do not expect adaptation alone to fix confabulation; desired behavior must be demonstrated in training data, and preference optimization may also be needed. section 1.11

A costly mismatch in financial analysis

A bank fine-tuned an 8B-parameter model on three years of earnings transcripts, spending eight weeks and $55K in compute. It learned financial language but could not answer questions about the latest call. Because the task required reasoning over live documents, RAG fit better than supervised fine-tuning. section 2.0

How LLM Customization and Fine-Tuning covers it

How deep it goes
Maps a technique continuum and lifecycle, but defers detailed recipes to later treatment.
Examples
Contrasts fine-tuning and RAG through a bank’s failed earnings-transcript system.
What it assumes
Requires a baseline and enough high-quality data; rejects adaptation when either is absent.
What you can do after
Apply a four-question framework to choose a starting adaptation technique for a project.
How it connects
Connects prompting, retrieval-augmented generation, LoRA, fine-tuning, distillation, alignment, and preference optimization.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of LLM Customization and Fine-Tuning. The section links point to the parts of the book it draws on.