Evaluating LLM Systems

Know the Vocabulary

This lesson uses the terms below many times. Read them once now, and come back here when a later section needs one.

• Generative system: A system whose output is new content, such as an answer, a summary, or a piece of code.
• Large language model (LLM): A model trained on a very large amount of text. It reads text in and writes text out.
• Prompt: The instructions and text that a system sends to an LLM for one request.
• Evaluation: Measuring how good a system's outputs are, so that two versions can be compared.