QuestionQ85

VerifiedAI Safety, Security, and Governance

A healthcare organization uses Amazon Bedrock to create a Retrieval Augmented Generation (RAG) application that assists practitioners with clinical decision-making. The application must provide high accuracy when retrieving patient information, detect hallucinations in generated content, and lower human-review costs.

Which solution meets these requirements?

Explanation

Amazon Bedrock RAG evaluations use an evaluator LLM to measure retrieval and response quality. Built-in retrieval metrics evaluate the relevance and coverage of retrieved context, and retrieve-and-generate metrics include faithfulness for detecting hallucinations relative to retrieved text, plus citation precision. Using LLM-as-a-judge screening with human review limited to edge cases preserves expert oversight while reducing the volume and cost of manual review.

Learn more

Community Discussion

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