Technique Aktualisiert 2026-04

Few-shot

Few-shot Learning
Definition

Few-shot involves providing a few examples in the prompt to guide the model toward the desired response format or style.

Siehe auch im Glossar

Z
Zero-shot
Zero-shot enables a model to accomplish a task without any prior examples, solely from the instruction.
P
Prompt
A prompt is the instruction or question you give an AI to get a response. It's the interface between you and the model.
P
Prompt Engineering
Prompt engineering is the art of crafting precise instructions to get the best results from an AI model.
L
LLM (Large Language Model)
An LLM is an AI model trained on billions of texts, capable of understanding and generating human language.

Tools, die few-shot verwenden

C
ChatGPT
Der weltweit meistgenutzte KI-Konversationsassistent
4.6/5
C
Claude
Die KI, die Nuancen versteht – von Anthropic
4.7/5
G
Gemini
Googles KI-Assistent mit 1-Million-Token-Kontext
4.5/5
M
Midjourney
Die Referenz in der KI-Bildgenerierung
4.4/5

Häufig gestellte Fragen

How many examples for few-shot?
Generally 2 to 5 examples are sufficient. Beyond that, marginal gains diminish and you consume tokens unnecessarily.
Does few-shot work for images?
Yes. On Midjourney, providing reference images is a form of visual few-shot. On Stable Diffusion, LoRAs are few-shot for styles.