consaf freshness

Author: PatrickFarley

articles/ai-services/content-safety/concepts/groundedness.md

@@ -6,7 +6,7 @@ author: PatrickFarley
 manager: nitinme
 ms.service: azure-ai-content-safety
 ms.topic: conceptual
-ms.date: 10/16/2024
+ms.date: 04/29/2025
 ms.author: pafarley
 ---
 
@@ -19,19 +19,10 @@ The Groundedness detection API detects whether the text responses of large langu
 - **Retrieval Augmented Generation (RAG)**: RAG is a technique for augmenting LLM knowledge with other data. LLMs can reason about wide-ranging topics, but their knowledge is limited to the public data that was available at the time they were trained. If you want to build AI applications that can reason about private data or data introduced after a model’s cutoff date, you need to provide the model with that specific information. The process of bringing the appropriate information and inserting it into the model prompt is known as Retrieval Augmented Generation (RAG). For more information, see [Retrieval-augmented generation (RAG)](https://python.langchain.com/docs/tutorials/rag/).
 - **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.
 
-## Groundedness detection options
-
-The following options are available for Groundedness detection in Azure AI Content Safety:
-
-- **Domain Selection**: Users can choose an established domain to ensure more tailored detection that aligns with the specific needs of their field. The current available domains are `MEDICAL` and `GENERIC`.
-- **Task Specification**: This feature lets you select the task you're doing, such as QnA (question & answering) and Summarization, with adjustable settings according to the task type.
-- **Speed vs Interpretability**: There are two modes that trade off speed with result interpretability.
-   - Non-Reasoning mode: Offers fast detection capability; easy to embed into online applications.
-   - Reasoning mode: Offers detailed explanations for detected ungrounded segments; better for understanding and mitigation.
 
 ##  Use cases
 
-Groundedness detection supports text-based Summarization and QnA tasks to ensure that the generated summaries or answers are accurate and reliable. Here are some examples of each use case:
+Groundedness detection supports text-based Summarization and QnA tasks to ensure that the generated summaries or answers are accurate and reliable.
 
 **Summarization tasks**:
 - Medical summarization: In the context of medical news articles, Groundedness detection can be used to ensure that the summary doesn't contain fabricated or misleading information, guaranteeing that readers obtain accurate and reliable medical information.
@@ -43,15 +34,9 @@ Groundedness detection supports text-based Summarization and QnA tasks to ensure
 - Educational QnA: In educational settings, the function can be applied to QnA tasks to confirm that answers to academic questions or test prep queries are factually accurate, supporting the learning process.
 
 
-## Groundedness correction
-
-The groundedness detection API includes a correction feature that automatically corrects any detected ungroundedness in the text based on the provided grounding sources. When the correction feature is enabled, the response includes a `corrected Text` field that presents the corrected text aligned with the grounding sources.
-
-###  Use cases
-
 Below, see several common scenarios that illustrate how and when to apply these features to achieve the best outcomes.
 
-#### Summarization in medical contexts
+### Summarization in medical contexts
 
 You're summarizing medical documents, and it’s critical that the names of patients in the summaries are accurate and consistent with the provided grounding sources.
 
@@ -72,7 +57,7 @@ Example API Request:
 
 The correction feature detects that `Kevin` is ungrounded because it conflicts with the grounding source `Jane`. The API returns the corrected text: `"The patient name is Jane."`
 
-#### Question and answer (QnA) task with customer support data
+### Question and answer (QnA) task with customer support data
 
 You're implementing a QnA system for a customer support chatbot. It’s essential that the answers provided by the AI align with the most recent and accurate information available.
 
@@ -93,10 +78,10 @@ Example API Request:
 ```
 **Expected outcome:**
 
-The API detects that `5%` is ungrounded because it does not match the provided grounding source `4.5%`. The response includes the correction text: `"The interest rate is 4.5%."`
+The API detects that `5%` is ungrounded because it doesn't match the provided grounding source `4.5%`. The response includes the correction text: `"The interest rate is 4.5%."`
 
 
-#### Content creation with historical data
+### Content creation with historical data
 
 You're creating content that involves historical data or events, where accuracy is critical to maintaining credibility and avoiding misinformation.
 
@@ -117,7 +102,7 @@ Example API Request:
 The API detects the ungrounded date `1065` and corrects it to `1066` based on the grounding source. The response includes the corrected text: `"The Battle of Hastings occurred in 1066."`
 
 
-#### Internal documentation summarization
+### Internal documentation summarization
 
 You're summarizing internal documents where product names, version numbers, or other specific data points must remain consistent.
 
@@ -138,6 +123,21 @@ Example API Request:
 
 The correction feature identifies `SuperWidget v2.1` as ungrounded and updates it to `SuperWidget v2.2` in the response. The response returns the corrected text: `"Our latest product is SuperWidget v2.2."`
 
+## Groundedness detection options
+
+The following options are available for Groundedness detection in Azure AI Content Safety:
+
+- **Domain Selection**: Users can choose an established domain to ensure more tailored detection that aligns with the specific needs of their field. The current available domains are `MEDICAL` and `GENERIC`.
+- **Task Specification**: This feature lets you select the task you're doing, such as QnA (question & answering) and Summarization, with adjustable settings according to the task type.
+- **Speed vs Interpretability**: There are two modes that trade off speed with result interpretability.
+   - Non-Reasoning mode: Offers fast detection capability; easy to embed into online applications.
+   - Reasoning mode: Offers detailed explanations for detected ungrounded segments; better for understanding and mitigation.
+
+## Groundedness correction
+
+The groundedness detection API includes a correction feature that automatically corrects any detected ungroundedness in the text based on the provided grounding sources. When the correction feature is enabled, the response includes a `corrected Text` field that presents the corrected text aligned with the grounding sources.
+
+
 ## Best practices
 
 Adhere to the following best practices when setting up RAG systems to get the best performance out of the groundedness detection API:
@@ -166,7 +166,7 @@ See [Query rates](/azure/ai-services/content-safety/overview#query-rates).
 
 If you need a higher rate, [contact us](mailto:[email protected]) to request it.
 
-## Next steps
+## Next step
 
 Follow the quickstart to get started using Azure AI Content Safety to detect groundedness.
 

articles/ai-services/content-safety/concepts/harm-categories.md

@@ -7,7 +7,7 @@ manager: nitinme
 ms.service: azure-ai-content-safety
 ms.custom: build-2023
 ms.topic: conceptual
-ms.date: 10/16/2024
+ms.date: 04/29/2025
 ms.author: pafarley
 ---
 
@@ -58,7 +58,7 @@ Every harm category the service applies also comes with a severity level rating.
 [!INCLUDE [severity-levels multimodal](../includes/severity-levels-multimodal.md)]
 
 
-## Next steps
+## Next step
 
 Follow a quickstart to get started using Azure AI Content Safety in your application.