AI-102 Implement generative AI solutions Practice Question
A team is using Azure OpenAI Service to summarize long legal contracts. They observe that summaries sometimes miss clauses located near the end of the document. The contracts are far longer than the model's maximum context window. What should they implement to improve coverage of the entire document?
⚠ Common exam trap
The trap here is assuming sampling parameters such as temperature or top_p influence how much source content the model can read, when they only affect token selection.
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
✓
Split the contract into overlapping chunks, summarize each chunk, then combine the partial summaries into a final summary.
Documents longer than the context window must be processed in pieces. Overlapping chunking ensures clauses spanning boundaries survive, and a combine step merges per-chunk summaries into a coherent whole. Sampling parameters and output length settings operate on generation behavior and cannot extend how much source text the model receives.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Lower the max_tokens parameter to force the model to read further into the document.
Why it's wrong here
Max_tokens limits the length of the generated output, not the input consumed. Reducing it shortens summaries and has no effect on how much of the contract the model processes. The missed clauses result from input truncation, which this parameter does not address.
- ✗
Increase the temperature parameter so the model explores more of the contract content.
Why it's wrong here
Temperature controls randomness in token selection, not how much of the document the model sees. The model still receives only the tokens that fit in the context window, so raising temperature cannot reveal clauses that were never included. It may also reduce summary consistency.
- ✗
Set the top_p parameter to 1.0 and rely on nucleus sampling to expand context coverage.
Why it's wrong here
Top_p, or nucleus sampling, restricts token selection to a cumulative probability mass. It shapes output diversity but does not extend the model's input capacity. Clauses beyond the context window remain unseen, so this setting cannot improve document-wide coverage.
- ✓
Split the contract into overlapping chunks, summarize each chunk, then combine the partial summaries into a final summary.
Why this is correct
Chunking with overlap followed by a combine step is the map-reduce pattern for documents exceeding the context window. Each chunk is summarized within limits, and overlap preserves clauses that straddle boundaries. Merging partial summaries produces coverage across the whole contract, addressing the missed end-of-document clauses.
Go deeper
Related to this question
About these practice questions
One of 761 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 →
JA
Written and reviewed by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
Last reviewed September 2026 · checked against the official Microsoft exam blueprint
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.