AI-102 Practice Question: Implement natural language processing solutions
You are using Azure AI Language's custom question answering feature to build a FAQ bot. The knowledge base contains many question-and-answer pairs. Users sometimes ask questions that are paraphrases of the stored questions. You need to improve the likelihood that the bot returns the correct answer for paraphrased questions. Which action should you take?
⚠ Common exam trap
The trap here is thinking that raising the confidence threshold improves answer quality for paraphrases, when it actually makes the bot stricter and more likely to return no answer.
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
✓
Add alternate questions to each question-and-answer pair in the knowledge base.
Adding alternate questions to each question-and-answer pair is the most direct way to improve matching for paraphrased queries. The service uses these variants to better understand different ways users might ask the same thing. Raising the threshold, accepting all active learning suggestions, or trying to change the embedding model do not reliably address the need to match paraphrases.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Enable active learning and accept all suggested question variants.
Why it's wrong here
Active learning suggests alternate questions based on user queries, which can help improve coverage. However, accepting all suggestions blindly may introduce noise or incorrect variants. While active learning is useful, it is not as direct or reliable as explicitly adding well-crafted alternate questions for each answer to handle paraphrases.
- ✓
Add alternate questions to each question-and-answer pair in the knowledge base.
Why this is correct
Alternate questions allow you to provide multiple phrasings for the same answer. When a user asks a paraphrased question, the service can match it to an alternate question and return the associated answer. This directly improves recall for variations in wording without changing the underlying model or adding unrelated content.
- ✗
Switch the knowledge base to use a different language model for embeddings.
Why it's wrong here
Custom question answering does not expose a setting to choose a different embedding model. The service manages the underlying ranking and matching. Changing the language model is not a supported action, and it would not be the correct approach to improve paraphrase matching; adding alternate questions is the supported method.
- ✗
Increase the confidence threshold for answer returns to 90.
Why it's wrong here
Raising the confidence threshold makes the bot more conservative, returning only answers when it is very confident. This would reduce false positives but also cause more paraphrased questions to fall below the threshold and receive no answer. It does not improve the model's ability to match paraphrases; it only filters results more aggressively.
Go deeper
Related to this question
About these practice questions
Courseiva writes every AI-102 question from scratch — 761 in total, each with an explanation and a wrong-answer breakdown. None are copied from real exams or 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.