Q80 — AWS AIF-C01 Ch.3

Question 80 of 100 | ← Chapter 3

A medical device company has added AI-generated product summaries to its online product catalog. The company wants to incorporate industry-specific terminology to improve output quality. An ML team has access to large volumes of unlabeled industry-specific standards and research documents. Which ML technique satisfies these requirements?

• A. Using prompt engineering to include edited examples in the next prompt
• B. Using Retrieval-Augmented Generation (RAG) to include relevant terminology
• C. Customizing the foundation model via continued pretraining on the dataset ✓
• D. Customizing the foundation model via instruction fine-tuning on an industry dataset

Correct Answer: C. Customizing the foundation model via continued pretraining on the dataset

Explanation

Given the need to integrate domain-specific terminology—and the availability of large volumes of *unlabeled* industry standards and research documents—RAG is the most appropriate technique. RAG dynamically retrieves relevant domain-specific content (e.g., definitions, specifications) from the corpus at inference time and injects it into the prompt, enabling accurate, context-aware generation without requiring labeled data or model retraining. This approach preserves model freshness, avoids hallucination of terminology, and leverages existing unstructured knowledge efficiently.