AWS prescriptive-guidance documentation change
Summary
Updated section headers and modified reference to security guardrails section
Security assessment
Header changes and link formatting update. Security guardrails reference remains informational without addressing new vulnerabilities.
Diff
diff --git a/prescriptive-guidance/latest/generative-ai-nlp-healthcare/evaluation.md b/prescriptive-guidance/latest/generative-ai-nlp-healthcare/evaluation.md index 0b10a595f..3d510992d 100644 --- a//prescriptive-guidance/latest/generative-ai-nlp-healthcare/evaluation.md +++ b//prescriptive-guidance/latest/generative-ai-nlp-healthcare/evaluation.md @@ -7 +7 @@ -Training and test dataMetrics +Training and test data for medical NLP tasksMetrics for medical NLP tasks @@ -25 +25 @@ Medical NLP tasks commonly use medical corpora (such as PubMed) or patient infor - * If required for your medical use case, implement guardrails and measure data bias and fairness. For example, make sure that the LLM prevents misdiagnosis due to racial profiles of patients. For more information, see the [Security and guardrails](./llms.html#llm-selection-guardrails) section in this guide. + * If required for your medical use case, implement guardrails and measure data bias and fairness. For example, make sure that the LLM prevents misdiagnosis due to racial profiles of patients. For more information, see _Security and guardrails_ in the [Choosing an LLM](./llms.html#llm-selection) section.