Adapting LLMs

P11.applied-llm-systems.02 · Audience: guest, it-ml, language-pro · Prerequisites: Agentic systems, tools & MCP

To make a general LLM good at a domain task you can pull three levers, in order of escalating commitment: prompt, fine-tune, distill. Prompting changes the input, fine-tuning changes the weights, distillation changes which model serves. (Cross-link: P10.llm-systems-frontier.04 — alignment & adaptation.) Adapting the model is one lever; which model to run per task, and what each token costs, is covered in P11.applied-llm-systems.05.

Step 1 / 4The three levers
LeverChangesData neededBest when
Promptthe input only (weights frozen)a handful of examplesship fast, little data, task fluid
Fine-tunethe weights (smaller model)100s–1000s of pairsreliable format, shorter prompts, small-beats-large
Distillwhich model servesthe teacher labels for youhit quality with a costly model, must serve cheap/fast

A fine-tuned small model can beat a prompted large one on a narrow task, while being cheaper to serve.

⚡ Interview Ref — the quick-scan Reference face
  • Three levers: prompt (input, frozen weights, few examples) · fine-tune (weights, 100s–1000s pairs, reliable format / small-beats-large) · distill (which model serves; teacher labels; cheap/fast serving).
  • Mental model: prompting changes the input, fine-tuning changes the weights, distillation changes which model serves.
  • Decision factors: labelled-data volume · need for reliable format · latency/cost constraint · existing teacher.
  • Distillation: teacher labels → student mimics → cheap fast serving at scale.
  • MoE: disambiguate sparse-expert layer vs model-router. VLMs: image-side tasks; grounded eval; images = sensitive data.
Ask the mentor about this module

Ask a question about this content. The mentor explains and grounds its answer in what you are studying; asking is recorded as a learning signal, not a grade.

Ctrl/Cmd + Enter to send

Try it yourself

A scratch console for this page's ideas — ungraded, nothing you run here is recorded.

Scratch console

A scratch console with the scientific stack (pandas, numpy, scikit-learn). Runs on the server — no network, resource-limited and measured.

Output appears here.