writer edits

Author: PatrickFarley

articles/ai-services/content-safety/includes/groundedness-detection-overview.md

@@ -18,7 +18,7 @@ The Groundedness detection feature detects whether the text responses of large l
 - **Groundedness and Ungroundedness in LLMs**: This refers to the extent to which the model's outputs are based on provided information or reflect reliable sources accurately. A grounded response adheres closely to the given information, avoiding speculation or fabrication. In groundedness measurements, source information is crucial and serves as the grounding source.
 
 
-##  Use cases
+## User scenarios
 
 Groundedness detection supports text-based Summarization and QnA tasks to ensure that the generated summaries or answers are accurate and reliable.
 

articles/ai-services/openai/concepts/content-filter-protected-material.md

@@ -10,9 +10,7 @@ ms.service: azure-ai-openai
 
 # Protected material detection filter
 
-The Protected material detection filter scans the output of large language models (LLMs) to identify and flag known protected material. This feature is designed to help organizations prevent the generation of content that closely matches copyrighted text or code.
-
-The Protected material detection filter scans the output of large language models to identify and flag known protected material. It is designed to help organizations prevent the generation of content that closely matches copyrighted text or code.
+The Protected material detection filter scans the output of large language models (LLMs) to identify and flag known protected material. It is designed to help organizations prevent the generation of content that closely matches copyrighted text or code.
 
 The Protected material text filter flags known text content (for example, song lyrics, articles, recipes, and selected web content) that might be output by large language models.
 

articles/ai-services/openai/concepts/content-filter.md

@@ -32,7 +32,7 @@ The content filtering system integrated in the Azure OpenAI Service contains:
 * Neural multi-class classification models aimed at detecting and filtering harmful content; the models cover four categories (hate, sexual, violence, and self-harm) across four severity levels (safe, low, medium, and high). Content detected at the 'safe' severity level is labeled in annotations but isn't subject to filtering and isn't configurable.
 * Other optional classification models aimed at detecting jailbreak risk and known content for text and code; these models are binary classifiers that flag whether user or model behavior qualifies as a jailbreak attack or match to known text or source code. The use of these models is optional, but use of protected material code model may be required for Customer Copyright Commitment coverage.
 
-## Risk categories
+## Filter categories
 
 The following table summarizes the risk categories supported by Azure OpenAI's content filtering system.
 

articles/ai-services/openai/toc.yml

@@ -60,7 +60,7 @@ items:
       items:
       - name: Content filtering overview
         href: ./concepts/content-filter.md
-      - name: Content filtering risk categories
+      - name: Content filtering severity levels
         href: ./concepts/content-filter-severity-levels.md
       - name: Prompt shields
         href: ./concepts/content-filter-prompt-shields.md