Zero-Shot

Performing a task with no examples and no training for it.

concept Prompting 4 relationships

Aperçu

Zero-shot means asking a model to do something it was not trained on and giving it no examples - only a description of the task. It solves the problem that every supervised approach needs labelled data for each new task, which does not scale to tasks nobody has collected data for. It exists as the capability that made general-purpose models useful, and as the upper bound that few-shot prompting is measured against.

Graphe des technologies

Comment Zero-Shot se rattache au reste de la pile.

Utilise et dépend de

LLM concept Models Zero-Shot based on LLM High ✓ source

Appliqué à

CLIP model Multimodal Zero-Shot used for CLIP High ✓ source
Prompt Engineering technique Prompting Zero-Shot used for Prompt Engineering High ✓ source

Alternatives

Few-Shot Learning technique
Une alternative à Zero-Shot · source

Comparaisons

Comparaisons détaillées avec les alternatives ci-dessus.

Few-Shot Learning vs Zero-Shot

Position de la technologie

AI
↓
Prompting
↓
concept
↓
Zero-Shot

Technologies liées

CLIP model
Few-Shot Learning technique
LLM concept
Prompt Engineering technique

Ressources officielles

Documentation

Dernière mise à jour: 2026-10-08
Dernière vérification: 2026-10-08

Sources citées

Chaque relation de cette page porte sa source.

arxiv.org 3 claims
arxiv.org 1 claim