# Few-Shot Prompting: In-Context Learning — Fine-tuning vs Prompting

Source: https://www.skillbyai.com/en/fine-tuning/p-fewshot

> Teach a pattern with examples placed in the prompt.

## The model adapts without any weight change

Large models can pick up a pattern from a few **examples in the prompt** (**in-context learning**). Nothing is trained: the examples are part of the input, so they are sent and paid for on **every call** and use context window. It is the best first move: immediate, needs few examples, easy to change. Limits: more examples cost more tokens, results depend on which examples and what order, and gains **flatten**. Choose diverse, representative, correct examples, include hard cases, and test the choice on your evaluation set.

## Examples in the prompt versus examples in the weights

Few-shot prompting learns instantly from a handful of examples but plateaus; training can use many more.

![Three ideas: show, plateau, cost.](assets/figures/fine-tuning/section-2-map.svg) — Figure 2.1 — Show, plateau and cost.

## A few-shot prompt (illustrative)

Three examples teach labels and format. Not run here.

```text
Classify each support ticket as billing, technical or other. Reply with the label only.

Ticket: "I was charged twice this month."       Label: billing
Ticket: "The app crashes when I open settings."   Label: technical
Ticket: "Do you have an office in Pune?"           Label: other

Ticket: "My invoice shows the wrong amount."      Label:
```

## Test example order

Shuffle the example order and compare scores; a big swing means the prompt is fragile and needs better examples.

**Quiz:** What does in-context learning mean?

- [ ] The model retrains overnight
- [x] The model adapts to a pattern from examples in the prompt, with no weights changed
- [ ] The model reads the internet live
- [ ] The model forgets its training

*Answer:* The model adapts to a pattern from examples in the prompt, with no weights changed. Examples in the prompt steer behaviour only for that call.