US 12,417,356 B2
Large-scale, privacy preserving personalized large language models (LLMs)
Michael Bendersky, Cupertino, CA (US); and Mingyang Zhang, San Jose, CA (US)
Assigned to Google LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on May 30, 2023, as Appl. No. 18/325,934.
Prior Publication US 2024/0403564 A1, Dec. 5, 2024
Int. Cl. G06F 40/35 (2020.01); G06N 20/00 (2019.01)
CPC G06F 40/35 (2020.01) [G06N 20/00 (2019.01)] 28 Claims
OG exemplary drawing
 
1. A computer-implemented method that when executed on data processing hardware causes the data processing hardware to perform operations comprising:
receiving a textual prompt from a user, the textual prompt corresponding to an utterance of terms input by the user to a user device associated with the user that specifies a task for a large language model (LLM) to perform;
obtaining a set of user features associated with the user;
determining, using the set of user features associated with the user, a user prompt embedding for the user;
processing, using the LLM, the textual prompt conditioned on the user prompt embedding for the user to generate a personalized response to the textual prompt; and
providing the personalized response to the textual prompt for output from the user device associated with the user.