• A technique in which a large language model (LLM) is provided with a small number of examples (typically 2–10) of a task before being asked to perform similar tasks on new inputs. This method leverages the model’s ability to recognize patterns from limited examples to generalize to new instances.

1. Related terms: One-shot prompting · Zero-shot prompting · Prompt engineering · Large language model
2. Previous term: Fetch priority
3. Next term: FFmpeg
4. Random term: First Interactive (webglossary.info/random 🎲)