CCARF Practice Question

Paper 1 · Question 30

D4 Prompt Engineering & Structured Output · Paper 1

Your extraction pipeline correctly identifies data in structured tables but returns empty fields when the same information appears in narrative paragraphs. Detailed instructions specify all required fields. What should you try first?

• A.Increase the model's context window to process more of the document
• B.Add few-shot examples showing correct extraction from both structured tables and narrative paragraphs
• C.Add a pre-processing step to convert all narrative text into tables
• D.Add a post-processing retry that re-extracts any empty fields

Show answer & explanations

Correct answer: B

A: The model already finds data in tables. The issue is not context size but inconsistent handling of different document structures.

B: Few-shot examples demonstrating correct handling of varied document structures directly address inconsistent extraction quality across formats.

C: This adds unnecessary complexity. The model should handle varied formats — few-shot examples teach it how.

D: Retrying without better guidance will produce the same empty results. The model needs examples of correct extraction from narrative text.

Related Prompt Engineering & Structured Output questions

More: Paper 1 · All practice questions