AWS Certified AI Practitioner (AIF-C01) — Question 210

Which large language model (LLM) parameter controls the number of possible next words or tokens considered at each step of the text generation process?

Answer options

• A. Maximum tokens
• B. Top K
• C. Temperature
• D. Batch size

Correct answer: B

Explanation

The correct answer is B, as the Top K parameter limits the number of highest probability tokens considered during generation, which influences the diversity of generated text. The other options do not directly relate to the selection process of next tokens: Maximum tokens sets a limit on response length, Temperature controls randomness, and Batch size refers to the number of input examples processed simultaneously.