AWS prescriptive-guidance documentation change
Summary
Updated section headers and formatting, modified bullet point formatting with asterisks, improved document structure for clarity
Security assessment
Changes involve formatting improvements and minor wording adjustments without any security-specific context or references to vulnerabilities, protections, or security features.
Diff
diff --git a/prescriptive-guidance/latest/rag-healthcare-use-cases/evaluation.md b/prescriptive-guidance/latest/rag-healthcare-use-cases/evaluation.md index 7d8431b9a..233aa0137 100644 --- a//prescriptive-guidance/latest/rag-healthcare-use-cases/evaluation.md +++ b//prescriptive-guidance/latest/rag-healthcare-use-cases/evaluation.md @@ -7 +7 @@ -Evaluating information extractionEvaluating multiple retrieversUsing an LLM +Evaluating information extractionEvaluating RAG solutions with multiple retrieversEvaluating a solution by using an LLM @@ -13 +13 @@ Evaluating the healthcare AI solutions you build is critical to making sure that -###### Topics +**Topics** @@ -24 +24 @@ Evaluating the healthcare AI solutions you build is critical to making sure that -## Evaluating the extraction of information +## Evaluating information extraction @@ -58 +58 @@ You can use a technique called _LLM-as-a-judge_ to evaluate the text responses f - * **Pairwise comparison** – Give the LLM evaluator a medical question and multiple responses that were generated by different, iterative versions of the RAG systems you created. Prompt the LLM evaluator to determine the best response based on response quality, coherence, and adherence to the original question. + * **Pairwise comparison** –**** Give the LLM evaluator a medical question and multiple responses that were generated by different, iterative versions of the RAG systems you created. Prompt the LLM evaluator to determine the best response based on response quality, coherence, and adherence to the original question. @@ -60 +60 @@ You can use a technique called _LLM-as-a-judge_ to evaluate the text responses f - * **Single-answer grading** – This technique is well suited for use cases where you need to evaluate the accuracy of categorization, such as patient outcome classification, patient behavior categorization, patient re-admission likelihood, and risk categorization. Use the LLM evaluator to analyze individual categorization or classification in isolation, and evaluate the reasoning it has provided against ground truth data. + * **Single-answer grading** –**** This technique is well suited for use cases where you need to evaluate the accuracy of categorization, such as patient outcome classification, patient behavior categorization, patient re-admission likelihood, and risk categorization. Use the LLM evaluator to analyze individual categorization or classification in isolation, and evaluate the reasoning it has provided against ground truth data.