CCARF Practice Question

Paper 3 · Question 53

D4 Prompt Engineering & Structured Output · Paper 3

[Scenario 6: Structured Data Extraction] You are building a structured data extraction system: pulling information from unstructured documents, validating output against JSON schemas, handling edge cases gracefully, and integrating with downstream systems. Your invoice schema marks vendor_tax_id as required. On invoices that genuinely lack a tax ID, the model fabricates plausible-looking values to satisfy the schema. What is the schema-level fix?

• A.Add a prompt instruction: “never fabricate tax IDs”
• B.Post-validate tax IDs against a checksum and discard failures
• C.Lower the temperature to make fabrication less creative
• D.Make the field optional/nullable so the model can legitimately return null when the information is absent from the source document

Show answer & explanations

Correct answer: D

A: pits an instruction against a structural requirement that demands a value

B: catches well-formed fabrications only by luck

C: makes invented values look more authoritative rather than preventing them

D: Required fields on possibly-absent information force fabrication — the schema leaves no honest answer. Nullable/optional fields give the model a legitimate way to say "not present," which is the designed prevention for this failure.

Related Prompt Engineering & Structured Output questions

More: Paper 3 · All practice questions