Exam AWS Certified AI Practitioner AIF-C01 topic 1 question 5 discussion

B not correct - The size of LLM may not affect the size of the output. C not correct - Temperature controls the creativity of the output, not size of the output. D not correct - Top-K controls number of next possible tokens, not size of the output. A is correct - In the prompt itself we can control various attributes of the output like size, language etc.

A: Adjust the prompt. Explanation: The behavior of a large language model (LLM) can be significantly influenced by the prompt it receives. To make the outputs short and written in a specific language, you can adjust the prompt to explicitly instruct the model to produce concise responses and specify the desired language. For example: "Provide a brief recommendation in Spanish." "Give a short response in French." This is the most direct way to align the output with the company’s expectations without requiring modifications to the model or its parameters.

Adjusting the prompt

A is correct

Adjusting the prompt will only help