US Patent Issued to INTUIT on Nov. 3 for "Contrastive in-context learning for large language models" (California Inventors)

ALEXANDRIA, Va., Nov. 3 -- United States Patent no. 12,783,894, issued on Nov. 3, was assigned to INTUIT INC. (Mountain View, Calif.).

"Contrastive in-context learning for large language models" was invented by Xiang Gao (Mountain View, Calif.) and Kamalika Das (Mountain View, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A contrastive in-context learning protocol for large language models. The protocol includes inputting positive and negative examples to a large language model. Additionally, the large language model may be instructed to analyze the reasons behind the positive examples being positive and the negative examples being negative. The large language model with such contrastive in-context l...