Implement generative AI solutions →hardMultiple ChoiceObjective-mapped

AI-102 Implement generative AI solutions Practice Question

Exhibit

{
  "completions": [
    {
      "prompt": "Generate a summary for the meeting notes: {notes}",
      "max_tokens": 150,
      "temperature": 0.7,
      "top_p": 1,
      "frequency_penalty": 0,
      "presence_penalty": 0,
      "stop": null
    }
  ]
}

Refer to the exhibit. You are using Azure OpenAI Service to generate summaries of meeting notes. The current configuration produces summaries that are too short and sometimes omit key points. How should you modify the parameters to get more complete summaries?

⚠ Common exam trap

Many exam-takers confuse parameters that control output length (max_tokens) with those that control output randomness (temperature, top_p) or repetition (frequency_penalty), leading them to incorrectly select options that affect style rather than completeness.

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

✓

Increase max_tokens to 300.

Increasing max_tokens to 300 allows the model to generate longer completions, which directly addresses the issue of summaries being too short and omitting key points. The max_tokens parameter sets the maximum number of tokens (words and punctuation) the model can produce in a single response, so raising it gives the model more capacity to include all necessary details from the meeting notes.

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 max_tokens to 300.
Why this is correct
Higher max_tokens allows longer completions.
✗
Decrease temperature to 0.3.
Why it's wrong here
Lower temperature makes output more deterministic but doesn't increase length.
✗
Increase frequency_penalty to 0.5.
Why it's wrong here
Frequency penalty reduces repetition, doesn't increase length.
✗
Set top_p to 0.9.
Why it's wrong here
Top_p affects sampling diversity, not completeness.

Go deeper

AI-102 Implement generative AI solutions Practice Question

Exhibit

Why each option matters

Option-by-option breakdown

Related to this question