ALEXANDRIA, Va., Nov. 3 -- United States Patent no. 12,783,856, issued on Nov. 3, was assigned to CISCO TECHNOLOGY INC. (San Jose, Calif.).
"Method to detect and fix hallucinations in generative Large Language Models" was invented by David C. White Jr. (St. Petersburg, Fla.) and Mohammed Izzat Hamzeh (Woluwe-Saint-Lambert, Belgium).
According to the abstract* released by the U.S. Patent & Trademark Office: "A system and method to detect a generative model's output to see if it is hallucinating or not, and to check the facts listed in the model. Additionally, when a hallucination or incorrect fact is detected, the correct fact can be applied as context to ask the model to regenerate the output again, taking the fact into consideration whil...