Skip to main content

XTM Cloud 26.2

Global Language Guard settings

The Language Guard feature is an AI-driven quality assurance (QA) check that ensures unbiased language by flagging offensive terms and suggesting alternatives. It promotes inclusive content by detecting and replacing potentially harmful words and phrases. It helps Linguists improve the translation quality with real-time feedback.

Important

You must connect your XTM Cloud instance to OpenAI GPT to use this feature. For details, see OpenAI GPT LLM configuration.

This QA check is supported for all language variants supported by OpenAI GPT. Currently, Language Guard  does not support consistency checks and extended table files in any format.

For optimal performance when connecting to OpenAI via Azure, we recommend that you use the 4o or 4o-mini model. We do not recommend the 3.5-turbo model or any OpenAI model with a GPQA benchmark score below 40%. Larger reasoning models, such as o1, o3-mini, or o1-preview, are also not recommended due to processing time limitations.

To display the Language Guard section, as a user with the XTM Cloud Administrator role, select Configuration > Settings > AI Control Center. Then, in the AI Control Center tab screen, select the Features sub-tab. Language Guard is one of the sections displayed in the Features tab screen.

In the Language Guard section, you see:

  • the Contact Sales button. It is displayed if the Language Guard feature has not been enabled for your XTM Cloud instance. Select this button to automatically generate an email message to our Sales team, with which you can request feature activation. Initially, some values in the message you generate are inserted by default, but you can adjust them and add other details to suit your requirements.

  • the Activated black_circle_checkmark.svg label. It indicates that the feature is currently active at global level. Project Managers can select the Language Guard QA check at project level.

  • the Manage button. Select it to:

In this section: