AI-102 Plan and manage an Azure AI solution Practice Question
A company is using Azure Form Recognizer to extract data from invoices. The prebuilt model does not correctly extract a custom field that is specific to the company's invoices. What is the most appropriate action to improve extraction accuracy for this field?
⚠ Common exam trap
Watch out — candidates often think prebuilt models can be customized via mapping or retraining, but Azure Form Recognizer prebuilt models are immutable and only custom models can be trained to recognize new fields.
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
✓
Train a custom model using labeled invoices that include the custom field.
The prebuilt Form Recognizer model is designed for common invoice layouts and may not recognize company-specific fields. Training a custom model with labeled invoices that include the custom field allows the model to learn the field's location and semantics, significantly improving extraction accuracy for that specific field.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✗
Use the prebuilt model with a custom field mapping.
Why it's wrong here
Field mapping only renames or repositions values the prebuilt model already extracts; it cannot add a field absent from the prebuilt schema, so the custom field remains unrecognised. Mapping is the right approach when the model extracts the value but you need it routed to a different output field.
- ✓
Train a custom model using labeled invoices that include the custom field.
Why this is correct
A custom model trained on labelled invoices teaches Form Recognizer the layout and semantics of the company-specific field, which the prebuilt invoice model cannot infer. Labelled samples supply the field's position and value patterns, directly improving extraction accuracy for that field.
- ✗
Adjust the confidence threshold for the prebuilt model.
Why it's wrong here
Confidence thresholds only filter which extracted values are returned or flagged; they cannot teach the model a field it was never trained to recognise, so the custom field stays unextracted. Threshold tuning is genuinely useful for balancing precision and recall on fields the prebuilt model already detects.
- ✗
Retrain the prebuilt model with additional invoices.
Why it's wrong here
Prebuilt models are immutable; you cannot retrain them, so no amount of extra invoices changes the schema. Training with your own labelled documents is correct when building a custom model, but here the requirement is extending the prebuilt invoice model with a company-specific field.
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 by Johnson Ajibi, MSc IT Security
Senior Network & Security Engineer · founder of Courseiva
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.