CCARF Practice Question

Paper 4 · Question 12

D4 Prompt Engineering & Structured Output · Paper 4

The moderation system uses tool_use with a JSON schema for classification output. All fields including 'sub_category' and 'target_demographic' are marked as required. Auditors discover that when a post is spam (which has no target demographic), the model fabricates plausible-sounding demographics like 'general public' or 'young adults.' What schema change prevents this fabrication?

Show answer & explanations

Correct answer: D

Related Prompt Engineering & Structured Output questions

Paper 4 Q3The moderation system classifies hate speech accurately for explicit slurs but misses coded language and dog-whistle terms that human modera…Paper 4 Q7A moderation team introduces a severity scale ('low', 'medium', 'high', 'critical'). The same post (a user threatening to 'destroy' a compet…Paper 4 Q16Your CI/CD pipeline processes code reviews using the Message Batches API. After a batch completes, you need to match each review result back…Paper 4 Q17The moderation system validates that every classification includes a 'reasoning' field explaining the decision. When validation fails (empty…Paper 4 Q22The moderation system's classification schema has a 'category' field defined as a free-text string. Auditors find 47 different category valu…

More: Paper 4 · All practice questions