Prompting & Inference
Zero-Shot Learning
Asking a model to do a task with no examples, relying only on instructions and what it already knows.
Zero-shot means the model tackles a task it was given no worked examples for, working purely from the instruction and its general training. Modern large language models are surprisingly good at this, which is why you can often just ask plainly and get a usable answer. When zero-shot falls short, adding a few examples, called few-shot, usually helps.
Reference: Wikipedia: Zero-Shot Learning
Related terms
Few-Shot Learning
Guiding a model by including a handful of examples in the prompt so it can follow the pattern.
In-Context Learning
A model’s ability to learn a task from examples placed in the prompt, without any change to its weights.
Prompt
The input you give a generative model, usually instructions or a question, that tells it what you want.