ALEXANDRIA, Va., May 5 -- United States Patent no. 12,619,649, issued on May 5, was assigned to INTUIT INC. (Mountain View, Calif.).
"Large language model input preprocessing and refinement" was invented by Shon Mendelson (Tel Aviv, Israel), Gal Elgavish (Tel Aviv, Israel), Hadar Lackritz (Tel Aviv, Israel) and Kaaleb Edery (Tel Aviv, Israel).
According to the abstract* released by the U.S. Patent & Trademark Office: "At least one processor can receive a text input from a user interface (UI) comprising at least a portion of a prompt to a large language model (LLM). The at least one processor can classify the text input as having a negative sentiment classification using a machine learning (ML) model configured to classify inputs according...