Intended Use

This model is designed to operate in English. Inputs can take many forms, from a single sentence to a list of sentences or even a large body of text. The output will identify sentences that appear to be "Not balanced", indicating a potential imbalance in the text.
Taking a string of text as input, the model performs a dual task. First, it provides an assessment of compliance, flagging the sentences that may be noncompliant. It also assigns risk levels to these sentences, with possible classifications being Low, Medium, or High. In addition, the model also identifies the category label for each potentially noncompliant sentence, denoting the type of imbalance detected.
These categories include:

• Promissory
• Exaggerated
• Misleading
• Unwarranted
  Thus, this model serves as a sophisticated tool for sentence-level analysis and risk assessment.

License

The use of this model is subject to the Saifr License Agreement available at https://saifr.ai/azure-custom-license Use of Saifr’s models is subject in all respects to the custom license agreement between Saifr and the end user.  Saifr models are not intended to replace the end user’s legal, compliance, business, or other functions, or to satisfy any legal or regulatory obligations.  Note that all compliance responsibilities remain solely those of the end user and that certain communications may require review and approval by properly licensed individuals.  Saifr is not responsible for determining compliance with rules and will not be liable for actions taken or not taken based on model use. 

Sample Inputs and Outputs (REST)

Example Request

You can use cURL or any REST Client to send request. Just add your token and test.

     curl https://<url.com> -X POST -d '{ "text": string, "risk_level": string }' -H "Authorization: Bearer <TOKEN>" -H "Content-Type: application/json"

Sample Input

{ "text": string, "risk_level": string }

where-

• text: The text corpus to check for noncompliance (Required)
• risk_level: The risk level for the sentence (Required). Allowed values -
  • Low
  • Medium
  • High

Sample Output

{
  "findings": [
    {
      "sentence": string,
      "label": string,
      "risk_level": string,
      "categories": string[]
    }
  ]
}

where-

• sentence: The input sentence that was checked for noncompliance.
• label: The label for the sentence. Possible values -
  • 'Balanced' - Denotes the sentence is balanced.
  • 'NotBalanced' - Denotes the sentence is not balanced.
• risk_level: The risk level for the sentence. Possible values -
  • 'Low'
  • 'Medium'
  • 'High'
• categories: Array of the category of noncompliance for the sentence. Possible values -
  • 'Promissory' - The input sentence may offer an illusion of safety or a promise.
  • 'Misleading' - The input sentence poses a risk that it is worse in reality.
  • 'Exaggerated' - The input sentence poses a risk that it is overstated.
  • 'Unwarranted' - The input sentence poses a risk that it is unsupported