Microsoft Research examines Copilot evaluation using synthetic enterprise data
Key point
Microsoft Research is examining methods to evaluate Microsoft Copilot using synthetic data to balance the protection of sensitive information with the need to capture complex organizational data.
Microsoft Research states that evaluating Microsoft Copilot at an enterprise scale requires test data that captures the full complexity of real organizations. However, real enterprise data contains sensitive information that cannot be used for evaluation under any circumstances.
The company is examining the transition from synthetic enterprise data evaluations to real Microsoft Copilot AI confidence.
This item is a summary. The full, checkable version is at the original source:
Read the original at Microsoft Research ↗