US Patent Issued to Databricks on March 17 for "Using LLM functions to evaluate and compare large text outputs of LLMs" (American, Polish Inventors)

ALEXANDRIA, Va., March 17 -- United States Patent no. 12,579,378, issued on March 17, was assigned to Databricks Inc. (San Francisco).

"Using LLM functions to evaluate and compare large text outputs of LLMs" was invented by Ridhima Gupta (Bellevue, Wash.), Prithvi Kannan (San Francisco), Sunish Sohil Sheth (San Jose, Calif.), Kasey Uhlenhuth (San Francisco), Hubert Zub (Bialystok, Poland) and Corey Zumar (Santa Clara, Calif.).

According to the abstract* released by the U.S. Patent & Trademark Office: "A method for evaluating textual output of one or more machine-learned language models is presented. The method includes receiving, from a user of a client device, a first prompt for input to one or more machine-learned language models, provi...