Techniques & Methods
Zero-Shot Learning
Zero-shot learning enables a model to handle tasks or categories it has never seen during training by generalizing from related knowledge. An LLM asked to translate a language it wasn't specifically trained on may still perform reasonably by leveraging cross-lingual patterns.
Zero-shot capability is a key measure of a model's generalization. Prompt engineering techniques help elicit zero-shot performance by framing tasks clearly without providing examples.
Authority Links
Related Terms
Techniques & Methods
Few-Shot Learning
Model's ability to generalize from only a handful of labeled examples.
Techniques & Methods
One-Shot Learning
Model's ability to learn and make accurate predictions from only a single example.
Techniques & Methods
Prompt Engineering
The discipline of designing input text — instructions, examples, constraints, and context — to reliably steer a language model toward accurate, well-formatted, and intent-aligned outputs without modifying model weights.
Techniques & Methods
Transfer Learning
Leveraging knowledge learned from one task or domain to improve performance on a related one.