Free Microsoft AI-900 Azure AI Fundamentals Actual Exam Questions - Question 5 Discussion

Question No. 5
Which parameter should you configure to produce a more diverse range of tokens in the responses
from a chat solution that uses the Azure OpenAI GPT-3.5 model?
Select one option, then reveal solution.
US
KN
Kevin N.
2026-02-22

C imo, presence penalty directly affects repetition, making responses less predictable.

0
KN
Kevin N.
2026-02-20

Option C seems right because presence penalty discourages repeating the same words, which naturally leads to more varied responses. The other options don’t really influence token diversity directly.

0
NZ
Naveed Z.
2026-02-14

It’s C. Presence penalty helps the model avoid repeating the same ideas, which encourages more varied output compared to just cutting off with a stop sequence like in D.

0
AU
Amit U.
2026-02-09

C/D? Presence penalty (C) makes the model avoid repeating tokens, which boosts diversity, while stop sequences (D) just cut off output, so less relevant. Definitely more about presence penalty here.

0
PA
Peter A.
2026-01-19

Maybe C, presence penalty affects diversity, but does the question mean token-level diversity or topic variety? Also, what’s the default setting here?

0