Question 160
During a Gen AI proof-of-value review, the team reports: A university revises course rules daily and expects source-backed assistant replies. Which proposed action should the responsible architect choose first?
Explanation
Correct Answer
“Choose retrieval for frequently changing external facts; reserve fine-tuning for an evaluated persistent task or behavior gap” is supported by this requirement: A university revises course rules daily and expects source-backed assistant replies. Fine-tuning modifies model behavior; retrieval supplies current external evidence. Verify it using fresh-document accuracy and traceable citations compared with a controlled no-retrieval baseline.
Incorrect Answers
“Assume fine-tuning guarantees faithful citation of documents not present during training” would not meet the requirement that a university revises course rules daily and expects source-backed assistant replies. Fine-tuning modifies model behavior; retrieval supplies current external evidence. The more reliable approach is to choose retrieval for frequently changing external facts; reserve fine-tuning for an evaluated persistent task or behavior gap.
“Retrain the model weekly to memorize every newly published policy clause” would not meet the requirement that a university revises course rules daily and expects source-backed assistant replies. Fine-tuning modifies model behavior; retrieval supplies current external evidence. The more reliable approach is to choose retrieval for frequently changing external facts; reserve fine-tuning for an evaluated persistent task or behavior gap.
“Embed user passwords into tuning samples to personalize future completions” would not meet the requirement that a university revises course rules daily and expects source-backed assistant replies. Fine-tuning modifies model behavior; retrieval supplies current external evidence. The more reliable approach is to choose retrieval for frequently changing external facts; reserve fine-tuning for an evaluated persistent task or behavior gap.