AI-102 Practice Question: Implement natural language processing solutions
You are designing a solution that uses Azure AI Language custom question answering. The knowledge base contains 200 question-answer pairs. Users report that the bot sometimes returns answers to questions that are semantically similar but not actually asked. You need to reduce these false positives while maintaining the ability to answer paraphrased questions. What should you configure?
⚠ Common exam trap
Many exam-takers confuse active learning with runtime filtering; active learning improves the model over time but does not change the immediate matching threshold.
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
✓
Increase the confidence threshold score for the project.
The confidence threshold determines the minimum score required for an answer to be returned. By increasing it, the bot becomes more selective, reducing false positives from semantically similar questions. Active learning and alternative questions improve coverage but do not directly filter low-confidence matches. The default answer is only a fallback and does not affect matching behavior.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Set the 'default answer' to a custom message indicating no answer was found.
Why it's wrong here
Changing the default answer only affects what the bot says when no answer meets the threshold. It does not change the matching logic or reduce false positives. If the threshold remains low, the bot will still return incorrect answers before reaching the default. The default answer is a fallback, not a precision control.
- ✗
Enable the 'Enable active learning' option.
Why it's wrong here
Active learning suggests alternative questions based on user queries and helps improve the knowledge base over time, but it does not directly filter out low-confidence matches in real time. It is a training aid, not a runtime filter. Enabling it will not immediately reduce false positives; it requires manual review and updates to the knowledge base.
- ✗
Add more alternative questions to each question-answer pair.
Why it's wrong here
Adding alternative questions can improve recall by covering more phrasings, but it does not address false positives. In fact, adding too many alternatives can increase the chance of incorrect matches. The goal is to reduce matches that are semantically similar but wrong, which requires a higher threshold, not more alternatives.
- ✓
Increase the confidence threshold score for the project.
Why this is correct
Raising the confidence threshold makes the bot return an answer only when the match score exceeds a higher value. This reduces false positives from semantically similar but incorrect matches. It still allows paraphrased questions to be answered if their score is high enough. The threshold is adjustable in the project settings and directly controls the trade-off between precision and recall.
Go deeper
Related to this question
About these practice questions
This AI-102 question is part of Courseiva's 761-question bank — original exam-style content with full explanations and wrong-answer analysis, never real exam questions or exam dumps. 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.