AWS Certified Generative AI Developer - Professional AIP-C01

By Amazon · Question Mode

QuestionQ9

Operational Efficiency and Optimization for GenAI Applications

A company uses Amazon Bedrock to create technical content for customers. The company has recently seen a surge in hallucinated outputs when its model produces summaries of lengthy technical documents. The outputs contain incorrect or invented details. The current solution uses a large foundation model (FM) with a basic one-shot prompt that supplies the complete document in one input.

The company needs a solution that reduces hallucinations and satisfies factual-accuracy objectives. The solution must process more than 1,000 documents per hour and provide summaries within 3 seconds for each document.

Which combination of solutions meets these requirements?

Choose two
Explanation

Retrieval Augmented Generation grounds summaries in semantically retrieved source chunks, reducing unsupported details while avoiding the cost and context limitations of passing an entire long document in one prompt. Amazon Bedrock Knowledge Bases automate document chunking, embeddings, retrieval, and response generation with source citations. Explicit chain-of-thought instructions that require fact verification add a prompt-level check for whether a proposed summary is supported by the provided evidence. Pattern-based output blocking does not establish factual grounding, higher temperature increases generation variability, and one-pass full-document prompting retains the original hallucination-prone design.

Learn more

Community Discussion

No comments yet. Be the first to start the discussion!