Describe features of generative AI workloads on Azure →mediumMultiple ChoiceObjective-mapped

AI-900 Practice Question: Describe features of generative AI workloads on Azure

A marketing team uses Azure OpenAI Service to generate product descriptions. They have a base description and want the model to produce multiple variations with different tones, such as formal, playful, and technical, while still being factually accurate. Which parameter should they adjust to control the randomness and diversity of the output?

⚠ Common exam trap

Microsoft often tests the distinction between temperature and top_p, where candidates mistakenly choose top_p because both affect randomness, but temperature is the primary parameter for controlling overall diversity and creativity in the output.

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

✓

temperature

Temperature controls the randomness of the model's output by scaling the logits before applying the softmax function. A higher temperature (e.g., 0.8) increases diversity and creativity, while a lower temperature (e.g., 0.2) makes the output more deterministic and focused. For generating product descriptions with different tones while maintaining factual accuracy, adjusting temperature is the correct approach.

Answer analysis

Option-by-option breakdown

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

✓
temperature
Why this is correct
Temperature is a sampling parameter that scales the logits (the raw prediction scores) before the model converts them into probabilities. A lower temperature (e.g., 0.2) makes the distribution sharper and more deterministic, producing conservative, focused copy that sticks closely to the most likely phrasing. A higher temperature (e.g., 0.8) flattens the distribution, enabling more unusual word choices, creative metaphors, and tonal variation—exactly what a marketing team needs when brainstorming product descriptions or taglines. It is the primary Azure OpenAI control for adjusting output randomness and creative tone.
✗
max_tokens
Why it's wrong here
max_tokens sets the absolute upper bound on the number of tokens (words or subword units) that the API will generate, acting like a word-count limit for the response. It does not affect the underlying probability distribution or sampling behavior, so two requests with the same prompt and different max_tokens values will draw from the same randomness and exhibit the same level of tonal variation. Its only effect is to cap response length—often cutting off a generation mid-sentence if the limit is reached—which means it cannot be used to make marketing copy more creative or varied.
✗
top_p
Why it's wrong here
top_p (nucleus sampling) is an alternative way to control randomness by selecting tokens with cumulative probability, but it is not the only or primary parameter for adjusting creativity; temperature is more commonly used for varying tone.
✗
frequency_penalty
Why it's wrong here
frequency_penalty applies a coefficient that reduces the logit score of a token each time it has already appeared in the generated sequence, thereby discouraging the model from repeating the same words or phrases. This directly addresses repetitiveness but does not change the overall entropy or the sampling temperature of the distribution, so it does not inherently make the text more creative or tonally diverse. In a marketing context, it helps avoid monotonous copy that keeps saying 'amazing' or 'best,' but it is not a substitute for temperature when the goal is to explore a broader range of stylistic variations.

Go deeper

AI-900 Practice Question: Describe features of generative AI workloads on Azure

Why each option matters

Option-by-option breakdown

Related to this question