- An approach in which a large language model (LLM) is asked to perform a task without being given any specific examples, relying solely on its pre-trained knowledge and the task description provided in the prompt. This technique tests the model’s ability to understand and execute tasks based purely on natural language instructions.
This term is sponsored by: your name/company?
- Previous term: Zero-indexed
- Next term: Zeroconf
- Random term: JavaScript XML (webglossary.info/random 🎲)