DP-100 Question #568: Real Exam Question with Answer & Explanation

Question

Note: This question is part of a series of questions that present the same scenario. Each question in the series contains a unique solution that might meet the stated goals. Some question sets might have more than one correct solution, while others might not have a correct solution. After you answer a question in this section, you will NOT be able to return to it. As a result, these questions will not appear on the review screen. You manage an Azure AI Foundry project in your subscription. You deploy a gpt-4o model. You must test the model before you use it in an existing front-end application. You need to adjust the parameters to get more creative responses. Solution: Adjust Presence penalty. Does the solution meet the goal?

Options

• AYes
• BNo

Explanation

{"question_number": 3, "correct_answer": "B", "explanation": "No, adjusting Presence Penalty does not meet the goal of getting more creative responses. Presence penalty (range: -2 to 2) penalizes a token if it has appeared anywhere in the output so far, regardless of how many times. This encourages the model to introduce new topics and avoid reusing terms it has already mentioned. While this can add topic diversity, it does not increase the model's fundamental creative output or randomness. Like frequency penalty, it is a repetition-management tool, not a primary creativity parameter. Temperature remains the correct parameter for this goal.", "generated_by": "claude-sonnet", "llm_judge_score": 4}

No community discussion yet for this question.