AB-731 Certification Practice Question #25

Question

You have a large language model (LLM) that was pretrained by using public data.

You want the LLM to generate responses that incorporate frequently updated proprietary content, such as internal documents and knowledge bases.

You need to recommend a solution to ensure that the LLM uses the most current information without retraining the model.

What should you include in the recommendation?

Accepted Answer

The requirement — incorporate frequently updated proprietary content without retraining the model — is the canonical RAG scenario: retrieve up-to-date internal documents at runtime and inject them into the prompt. Prompt engineering (B) adds no new knowledge, content filtering (C) is a safety control, and fine-tuning (D) is explicitly excluded because it retrains the model. Suggested Answer, the commenter, and MS Learn all select A.

More AB-731 practice questions