ALEXANDRIA, Va., June 2 -- United States Patent no. 12,645,892, issued on June 2, was assigned to TENCENT AMERICA LLC (Palo Alto, Calif.).
"Advantage modeling for RLHF" was invented by Baolin Peng (Palo Alto, Calif.), Linfeng Song (Palo Alto, Calif.) and Haitao Mi (Palo Alto, Calif.).
According to the abstract* released by the U.S. Patent & Trademark Office: "A method and apparatus comprising computer code configured to cause a processor or processors to receive an input question to the LLM, model an advantage for the input question based on at least one of a multi-gaussian mixed matrix (GMM) model and an entropy regularizer, and train the LLM based on the advantage, and the advantage includes a proximal policy optimization (PPO) objectiv...