Implement generative AI solutions →hardMultiple Choice

AI-102 Implement generative AI solutions Practice Question

Exhibit

{
  "completions": [
    {
      "prompt": "Generate a summary of the following text: ...",
      "parameters": {
        "temperature": 0.3,
        "max_tokens": 150,
        "top_p": 0.9,
        "frequency_penalty": 0.0,
        "presence_penalty": 0.0
      },
      "response": "..."
    }
  ]
}

Refer to the exhibit. You are configuring an Azure OpenAI Service deployment for document summarization. The current parameters produce summaries that are often too verbose. You need to make the summaries more concise while maintaining factual accuracy. Which parameter change should you make?

⚠ Common exam trap

Microsoft often tests the distinction between parameters that control output length (max_tokens) versus those that control creativity or diversity (temperature, top_p, frequency_penalty), leading candidates to mistakenly adjust the latter when the issue is simply excessive length.

Answer choices

Why each option matters

Answer the question above first, then reveal the full breakdown to understand why each option is right or wrong.

Correct answer & explanation

✓

Decrease max_tokens to 100

Decreasing max_tokens to 100 directly limits the maximum length of the generated summary, forcing the model to produce shorter output. This addresses the verbosity issue without altering the model's factual accuracy, as max_tokens controls output length, not content selection or creativity.

Answer analysis

Option-by-option breakdown

For each option: why learners choose it and why it is or isn't the right answer here.

✗
Increase top_p to 1.0
Why it's wrong here
Increasing top_p may increase diversity but not conciseness.
✗
Increase frequency_penalty to 0.5
Why it's wrong here
Frequency_penalty discourages repeated tokens, so it curbs looping phrases but does not shorten overall output; a verbose summary can remain verbose while merely avoiding repetition. It is chosen when generated text repeats identical words or phrases, not when length itself must be reduced.
✓
Decrease max_tokens to 100
Why this is correct
Lowering max_tokens caps the response length, directly curbing verbosity by truncating generation before padding accumulates. However, it constrains output size rather than steering style, so factual accuracy is preserved only if essential content fits within 100 tokens; summarisation quality may suffer if key facts are cut off.
✗
Increase temperature to 0.7
Why it's wrong here
Raising temperature to 0.7 increases sampling randomness, producing more varied wording and a greater chance of drifting from source facts, which worsens verbosity control. Temperature is tuned for creative or diverse generation; for summarisation, lowering it toward zero keeps output deterministic and grounded in the document.

Go deeper

AI-102 Implement generative AI solutions Practice Question

Exhibit

Why each option matters

Option-by-option breakdown

Related to this question