logo

For the Inventor, By the Inventor

The patent badge is an abbreviated version of the USPTO patent document. The patent badge does contain a link to the full patent document.

The patent badge is an abbreviated version of the USPTO patent document. The patent badge covers the following: Patent number, Date patent was issued, Date patent was filed, Title of the patent, Applicant, Inventor, Assignee, Attorney firm, Primary examiner, Assistant examiner, CPCs, and Abstract. The patent badge does contain a link to the full patent document (in Adobe Acrobat format, aka pdf). To download or print any patent click here.

Patent No.:

US 12783818 B1

PDFFull Text
Date of Patent:
Nov. 03, 2026

Filed:

Aug. 08, 2023

Reducing computational resource usage via training and/or utilizing large language models

Applicant:

Google Llc, Mountain View, CA (US);

Inventors:

Ragha Kotikalapudi, San Jose, CA (US);

Chen Zhu, Palo Alto, CA (US);

Steven Zheng, San Bruno, CA (US);

Sahitya Potluri, Sunnyvale, CA (US);

Yu Du, Sunnyvale, CA (US);

Heng-Tze Cheng, Mountain View, CA (US);

Quoc Le, Sunnyvale, CA (US);

Ed H. Chi, Los Altos, CA (US);

Assignee:

GOOGLE LLC, Mountain View, CA (US);

Attorney:

Gray Ice Higdon

Primary Examiner:

Richa Sonifrank

Int. Cl.
CPC ...
G06F 40/40 (2020.01); G06F 16/3329 (2025.01); G06F 16/334 (2025.01); G06F 16/338 (2019.01); G06F 40/279 (2020.01); G06F 40/30 (2020.01); G06F 40/35 (2020.01); G06F 40/56 (2020.01); G06N 3/006 (2023.01); G06N 3/045 (2023.01); G06N 3/0475 (2023.01); G06N 3/08 (2023.01); G06N 3/09 (2023.01); G06N 20/00 (2019.01); G06N 20/20 (2019.01);
U.S. Cl.
CPC ...
G06F 40/40 (2020.01); G06F 16/3329 (2019.01); G06F 16/3344 (2019.01); G06F 40/279 (2020.01); G06F 40/30 (2020.01); G06F 40/35 (2020.01); G06F 40/56 (2020.01); G06N 3/006 (2013.01); G06N 3/045 (2023.01); G06N 3/08 (2013.01); G06N 3/09 (2023.01); G06N 20/00 (2019.01); G06F 16/338 (2019.01); G06N 3/0475 (2023.01); G06N 20/20 (2019.01);
Abstract

Implementations described herein relate to using self-evaluation when utilizing a large language model (LLM) to generate a response to a natural language (NL) based input. The LLM can be used to process the NL based input to generate a plurality of responses, and to generate a critique of those responses by comparing the responses to a set of response evaluation criteria. One of the responses can then be selected based on the comparison with the set of response evaluation criteria which can vary from one NL based input to another. If the NL based input was obtained a user of a client device during an inference stage, then the selected response can be rendered for presentation to the user. If the NL based input was obtained during a training stage, then the selected response can be stored as a training instance and optionally in association with additional data.

Find Patent Forward Citations

Quick Actions:

Kotikalapudi, Ragha. (2026). Reducing computational resource usage via training and/or utilizing large language models (U.S. Patent No. 12783818). U.S. Patent and Trademark Office. https://idiyas.com/patent/badge/12783818

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

Loading…