Courseiva
Implement generative AI solutionsmediumMultiple ChoiceObjective-mapped

AI-102 Implement generative AI solutions Practice Question

Exhibit

{
  "deployment": {
    "model": "gpt-35-turbo",
    "modelVersion": "0613",
    "scaleSettings": {
      "scaleType": "Standard"
    },
    "properties": {
      "maxTokens": 4096,
      "temperature": 0.7,
      "topP": 0.95,
      "frequencyPenalty": 0,
      "presencePenalty": 0
    }
  }
}

Refer to the exhibit. You have deployed a GPT-3.5 Turbo model in Azure OpenAI Service with the shown configuration. Users report that the model generates responses that are too repetitive. You need to reduce repetition. Which parameter should you modify?

⚠ Common exam trap

Watch out — candidates often confuse presencePenalty with frequencyPenalty, assuming both address repetition equally, but presencePenalty specifically targets repetition of already-seen tokens in the current response, making it the correct choice for this scenario.

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 presencePenalty to 0.5

Increasing the presencePenalty parameter penalizes tokens that have already appeared in the generated text, encouraging the model to introduce new topics and reduce repetition. In Azure OpenAI Service, presencePenalty directly influences the logit scores of previously seen tokens, making them less likely to be selected again, which addresses the user's complaint of overly repetitive responses.

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 presencePenalty to 0.5

    Why this is correct

    Presence penalty reduces the likelihood of repeating any token that has appeared, reducing repetition.

  • Increase frequencyPenalty to 0.5

    Why it's wrong here

    Frequency penalty reduces repetition of frequent tokens, but presence penalty is more effective for this scenario.

  • Increase temperature to 1.0

    Why it's wrong here

    Increasing temperature increases randomness, not reducing repetition.

  • Decrease topP to 0.5

    Why it's wrong here

    Decreasing topP reduces diversity, not repetition.

About these practice questions

One of 945 original AI-102 practice questions on Courseiva, each with a full explanation and wrong-answer analysis — not exam dumps or protected exam content. Learn why practice questions differ from exam dumps →

How Courseiva writes practice questions · Editorial policy

JA

Written by Johnson Ajibi, MSc IT Security

Senior Network & Security Engineer · founder of Courseiva

This AI-102 practice question is part of Courseiva's free Microsoft certification practice question bank. Courseiva provides original exam-style practice questions with explanations, topic-based practice, mock exams, readiness tracking, and study analytics to help learners prepare for the AI-102 exam.