Zero-shot Learning
Quick Answer
Zero-shot learning is when a model performs a task it was never explicitly trained on, by generalising from related knowledge. Modern LLMs routinely perform useful zero-shot classification, extraction and generation tasks with no task-specific training examples.
In Depth
What Zero-shot Learning really means
Zero-shot capability is one of the most transformative features of modern generative models. A product team can prototype a new capability in minutes by writing a well-crafted prompt, rather than collecting thousands of labelled examples.
The trade-off is that zero-shot quality is often lower than fine-tuned or few-shot performance. Teams typically start zero-shot, validate the use case, then invest in few-shot examples or fine-tuning only if accuracy needs lift.
Why It Matters
Business relevance for UK organisations
Zero-shot learning collapses prototype timelines from weeks to hours, making it cost-effective for SMEs to experiment with a wide portfolio of AI use cases before investing in the winners.
Real-world example
How this shows up in practice
A Manchester SaaS team prototyped four AI features in a single week using zero-shot prompts, shortlisting two for production investment based on user feedback.
Related Terms
Continue exploring
Few-shot Learning
Few-shot learning is when a model learns a new task from a small number of examples, often supplied directly in the prompt. It sits between zero-shot (no examples) and full fine-tuning (many examples) and offers an excellent balance of quality and effort.
TechnicalPrompt Engineering
Prompt engineering is the practice of designing the text instructions given to a language model to produce reliable, accurate and appropriate outputs. Good prompts unlock significantly better performance without any change to the underlying model.
TechnicalLarge Language Model (LLM)
A Large Language Model (LLM) is a type of neural network trained on vast quantities of text to understand and generate human language. LLMs power chatbots, copilots, content generators and many modern AI features across consumer and business software.
TechnicalFine-tuning
Fine-tuning is the process of further training a pre-trained model on a smaller, task-specific dataset so that it specialises in a particular domain, tone or set of behaviours. It sits between using a base model as-is and training a new model from scratch.