Improve Field Extraction Accuracy in Azure Document Intelligence
A company uses Azure Document Intelligence to extract data from tax forms. They need to improve accuracy for a specific field. Which TWO actions should they take?
Quick Answer
The answer is to train a custom model using at least five similar forms and label more examples of the specific field in the training set. This works because Azure Document Intelligence’s custom extraction models rely on supervised learning: providing additional ground-truth annotations for the target field directly teaches the model to recognize variations in handwriting, formatting, and layout, which is the most effective way to improve field accuracy. On the AI-102 exam, this scenario tests your understanding of how custom model training differs from prebuilt models—a common trap is assuming you can simply adjust confidence thresholds or use a prebuilt tax model, but those do not refine extraction for a single custom field. Remember the “five-plus rule”: for targeted accuracy gains, you need at least five labeled examples per field, and more is better. A useful memory tip is “label more, score higher”—the more varied examples you annotate for that one field, the sharper the model’s extraction becomes.
⚠ Common exam trap
A common mix-up: candidates confuse prebuilt models with custom models, assuming that prebuilt models can be retrained or fine-tuned, when in fact they are static and cannot be customized for specific field accuracy improvements.
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
✓
Label more examples of the specific field in the training set
Labeling more examples of the specific field in the training set directly provides the custom model with additional ground-truth annotations for that field. This increases the model's ability to learn the variations in handwriting, formatting, and layout for that field, which is the most effective way to improve extraction accuracy for a targeted field in Azure Document Intelligence custom models.
Answer analysis
Option-by-option breakdown
For each option: why learners choose it and why it is or isn't the right answer here.
- ✓
Label more examples of the specific field in the training set
Why this is correct
More labeled examples improve model accuracy for that field.
- ✗
Increase the batch size in the analysis request
Why it's wrong here
Batch size does not affect accuracy.
- ✗
Reduce the image resolution to 200 DPI
Why it's wrong here
Lower resolution reduces OCR accuracy.
- ✗
Use the prebuilt-tax.us model
Why it's wrong here
Prebuilt models may not extract custom fields accurately.
- ✓
Train a custom model using 10 similar forms
Why this is correct
Custom models trained on similar forms yield better accuracy.
Go deeper
Related to this question
About these practice questions
One of 945 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 →
Same concept, more angles
1 more way this is tested on AI-102
These questions test the same concept from different angles. Work through them to make sure you can recognise it however the exam phrases it.
Variation 1. A healthcare organization uses Azure Document Intelligence to process patient intake forms. They notice that the confidence scores for field extraction are low. What is the most likely cause?
easy- A.The document resolution is too low
- B.The document layout is not analyzed
- ✓ C.The custom model was trained with only 10 labeled forms
- D.The batch processing size is too large
Why C: Custom models in Azure Document Intelligence require a minimum of five labeled forms for training, but low confidence scores typically indicate insufficient training data. With only 10 labeled forms, the model lacks enough examples to generalize well across variations in handwriting, formatting, and field values, leading to poor extraction confidence.
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.