AI-102 Implement generative AI solutions Practice Question
You are using Azure OpenAI Service to generate marketing copy. The marketing team reports that the generated content sometimes contains factual inaccuracies. You need to improve the factual accuracy of the generated content. What should you do?
⚠ Common exam trap
AI-102 often tests the misconception that lowering temperature or increasing tokens improves factual accuracy — candidates must recognize that grounding with context (RAG) is the correct approach to reduce hallucinations.
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
✓
Include relevant context and facts in the prompt
The most effective way to improve factual accuracy in Azure OpenAI generations is to ground the model with relevant context and facts in the prompt — this is the core of Retrieval-Augmented Generation (RAG). By supplying authoritative source content, the model conditions its output on verified information rather than relying solely on parametric memory, which reduces hallucinations. This directly addresses the marketing team's complaint about factual inaccuracies.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Increase the max_tokens parameter
Why it's wrong here
max_tokens caps response length; raising it lets the model write longer text without adding any factual grounding, so inaccuracies persist. It is tempting because truncation can cut answers short, but the actual mechanism needed is supplying authoritative source content so the model conditions on verified facts.
- ✓
Include relevant context and facts in the prompt
Why this is correct
Grounding the model with relevant facts and context in the prompt constrains generation to supplied information, reducing hallucinated claims. This directly addresses the factual inaccuracy problem by giving the model authoritative source material rather than relying on parametric knowledge alone.
- ✗
Decrease the temperature parameter
Why it's wrong here
Temperature controls sampling randomness, so lowering it makes outputs more deterministic and repetitive, not more factually grounded. It is tempting because lower temperature is commonly recommended for consistent responses, but factual accuracy requires grounding the model in retrieved, verifiable source content rather than altering sampling behaviour.
- ✗
Disable content filtering
Why it's wrong here
Content filtering screens harmful categories such as hate and violence; it does not verify factual claims, so disabling it removes a safety control while leaving hallucinations untouched. It is tempting because filtering can appear to alter output, but its actual purpose is moderation, and it would be the right choice only when tuning safety thresholds, not accuracy.
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.