mediumMultiple Choice
AI-102 Practice Question: A company uses Azure Form Recognizer to extract…
A company uses Azure Form Recognizer to extract data from invoices. The extracted data contains many errors for a specific vendor's invoices. What should they do?
⚠ Common exam trap
Many exam-takers assume increasing the confidence threshold (Option C) will fix extraction errors, but it only filters results rather than improving the underlying model's accuracy for vendor-specific formats.
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
✓
Custom train a model with labeled examples of that vendor's invoices.
Azure Form Recognizer's prebuilt invoice model may not generalize well to vendor-specific layouts or data formats. By custom training a model with labeled examples of that vendor's invoices, you adapt the extraction to the unique fields, tables, and formatting, significantly reducing errors. This leverages the service's supervised learning capability to improve accuracy for domain-specific documents.
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 a different prebuilt model.
Why it's wrong here
A different prebuilt model still applies generic invoice fields, so it cannot resolve this vendor's layout quirks. The custom model route exists precisely for vendor-specific templates: train on labelled samples to capture that format. Prebuilt models suit standard, consistent invoices across many suppliers.
- ✗
Disable the OCR step.
Why it's wrong here
OCR is the extraction engine itself; disabling it removes all text recognition, so no fields can be returned for any vendor. The errors stem from that vendor's invoice layout, so the fix is training a custom model or adding labelled samples. OCR would be disabled only when documents are already machine-readable, such as native PDFs with embedded text.
- ✗
Increase the confidence threshold.
Why it's wrong here
Raising the confidence threshold only filters low-confidence results; it cannot correct the underlying extraction errors, and may discard valid fields. Thresholds suit scenarios where you must suppress uncertain output before downstream processing, not where a vendor's layout consistently misparses.
- ✓
Custom train a model with labeled examples of that vendor's invoices.
Why this is correct
A custom model trained on labelled examples of that vendor's invoice layout teaches Form Recognizer the specific field positions and terminology it misreads, unlike the prebuilt invoice model. This directly addresses the vendor-specific extraction errors by adapting the model to that template's structure.
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 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.