Pattern matching
Pattern matching is a model’s tendency to continue the structure it has been shown, which is why consistent examples change output more reliably than described rules.
It explains several practical effects: inconsistent examples produce inconsistent output, a single formatting slip in a few-shot block propagates, and showing one correct answer usually beats a paragraph explaining what a correct answer looks like.
Related terms
- Few-shot prompting
- Few-shot prompting is giving a model several worked examples of a task inside the prompt so it can infer the pattern and apply it to new input.
- One-shot prompting
- One-shot prompting is giving a model exactly one worked example of the task before asking it to perform that task.
More on techniques
See the full glossary, read the guides, or put it into practice in the prompt builder.