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?

The correct answer is C. Presence penalty. Presence penalty increases the likelihood of introducing new topics in a response or penalizes tokens based on whether they have already appeared in the text. Presence penalty encourages using different words, providing diverse context meanings…

Submitted by anjalisingh· Mar 30, 2026Describe features of generative AI workloads on Azure

Question

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?

Options

AMax response
BPast messages included
CPresence penalty
DStop sequence

How the community answered

(40 responses)

A
5% (2)
B
3% (1)
C
75% (30)
D
18% (7)

Explanation

Presence penalty increases the likelihood of introducing new topics in a response or penalizes tokens based on whether they have already appeared in the text. Presence penalty encourages using different words, providing diverse context meanings. https://learn.microsoft.com/en-us/azure/ai-services/openai/chatgpt-quickstart

Topics

#Azure OpenAI#GPT-3.5#presence penalty#token diversity

Community Discussion

No community discussion yet for this question.

Full AI-900 Practice