ALEXANDRIA, Va., Jan. 13 -- United States Patent no. 12,524,711, issued on Jan. 13.
"Parameter efficient prompt tuning for efficient models at scale" was invented by Brian David Lester (Mountain View, Calif.), Rami Al-Rfou (Menlo Park, Calif.) and Noah Constant (Los Angeles).
According to the abstract* released by the U.S. Patent & Trademark Office: "Systems and methods for natural language processing can leverage trained prompts to condition a large pre-trained machine-learned model to generate an output for a specific task. For example, a subset of parameters may be trained for the particular task to then be input with a set of input data into the pre-trained machine-learned model to generate the task-specific output. During the trainin...