A language model generates text one token at a time. At each step it produces a probability for every possible next token and then samples one. Request parameters change how that sampling works and when generation stops, so the same prompt can produce focused, repeatable answers or varied, creative ones. The exam expects you to choose the right parameter for a described behavior.
Free account
Keep reading for free
Create a free StudyToCert account to read the rest of this lesson: 5 more sections, 4 key terms, a real-world example, an exam tip and self-check questions. Every lesson, lab and practice test is free with an account.