Microsoft patents method to check AI answers against verified facts
Microsoft has patented a system that checks if a generative AI's answer matches a list of pre-approved, correct question-and-answer pairs. If the AI's response is similar enough to a verified pair, the system allows the answer to be sent to the user and records the interaction.
In the filing’s own words
A method, computer program product, and computing system for processing a prompt for a target generative AI model and a corresponding response generated by the target generative AI model for the prompt. The prompt and the corresponding response from the generative AI model are compared to a plurality of predefined verified prompt-response pairs. In response to determining at least a threshold similarity between the prompt and the corresponding response and a predefined verified prompt-response pair, the corresponding response from the target generative AI model is provided to a source of the prompt.
What exactly they claim (claim 1)
1. A computer-implemented method, executed on a computing device, comprising: generating a first embedding representing a prompt directed to a target generative artificial intelligence (AI) model and a second embedding representing a corresponding response generated by target generative AI model based on the prompt; performing a vector similarity search on the first embedding and the second embedding with respect to embeddings representing prompts and responses of a plurality of predefined verified prompt-response pairs; and in response to determining, based on the vector similarity search, at least a threshold similarity between the prompt and the corresponding response and a predefined verified prompt-response pair of the plurality of predefined verified prompt-response pairs: providing the corresponding response from the target generative AI model to a source of the prompt; and managing feedback applied to the target generative AI model.
Facts
- Company
- Microsoft (Microsoft Technology Licensing, LLC)
- Official title
- System and method for proactively reducing hallucinations in generative artificial intelligence (AI) model responses
- Patent number
- US12769935B2
- Application number
- 18508470
- Filed
- Nov 14, 2023
- Granted
- Oct 20, 2026
- Inventors
- 2
- Claims
- 19
Classified under
G06F 40/20 Physics & computingMore from Microsoft in AI & software
- Microsoft patents AI that presents PowerPoint slides for you Sep 3, 2026
- Microsoft patents method to check if LLM answers are based on real data Sep 10, 2026
- Microsoft patents system to blend multiple AI agents into one chat Oct 1, 2026
- Microsoft patents system that answers questions using your screen history Oct 15, 2026
- Microsoft patents AI tool that writes and runs software tests from text Sep 1, 2026
Summaries are simplified from the filing’s own abstract and first claim. A patent filing is not a product announcement.
Patent data and drawings: U.S. Patent and Trademark Office (USPTO). Nebula is not affiliated with or endorsed by the USPTO.