Merge pull request #9 from microsoft/update-transp-notes

docs: update transparency notes formatting

Author: toherman-msft

TRANSPARENCY_FAQ.md

@@ -23,7 +23,9 @@
 
 - ### What are the limitations of the Content Processing Solution Accelerator? How can users minimize the Content Processing Solution Accelerator’s limitations when using the system?   
 
-  This solution accelerator can only be used as a sample to accelerate the creation of content processing solutions. The repository showcases a sample scenario of a Data Analyst at a property insurance company, analyzing large amounts of claim-related data, but a human must still be responsible to validate the accuracy and correctness of data extracted for their documents, schema definitions related to business specific documents to be extracted, quality and validation scoring logic and thresholds for human-in-the-loop review, ingesting transformed data into subsequent systems, and their relevancy for using with customers. Users of the accelerator should review the system prompts provided and update as per their organizational guidance. AI generated content in the solution may be inaccurate and the outputs and integrated solutions derived from the output data is not robustly trustworthy and should be manually reviewed by the user. You can find more information on AI generated content accuracy at https://aka.ms/overreliance-framework.
+  This solution accelerator can only be used as a sample to accelerate the creation of content processing solutions. The repository showcases a sample scenario of a Data Analyst at a property insurance company, analyzing large amounts of claim-related data, but a human must still be responsible to validate the accuracy and correctness of data extracted for their documents, schema definitions related to business specific documents to be extracted, quality and validation scoring logic and thresholds for human-in-the-loop review, ingesting transformed data into subsequent systems, and their relevancy for using with customers. Users of the accelerator should review the system prompts provided and update as per their organizational guidance. 
+  
+  AI generated content in the solution may be inaccurate and the outputs and integrated solutions derived from the output data are not robustly trustworthy and should be manually reviewed by the user. You can find more information on AI generated content accuracy at https://aka.ms/overreliance-framework.
 
   Currently, the sample repository is available in English only and is only tested to support PDF, PNG, and JPEG files up to 20MB in size.