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.

Date of Patent:
Nov. 17, 2026

Filed:

Feb. 01, 2024
Applicant:

Adobe Inc., San Jose, CA (US);

Inventors:

Ryan A. Rossi, Santa Clara, CA (US);

Xiang Chen, Palo Alto, CA (US);

Tong Yu, Fremont, CA (US);

Sungchul Kim, San Jose, CA (US);

Subrata Mitra, Bangalore, IN;

Shunan Guo, San Jose, CA (US);

Ryan Alexander Aponte, Pittsburgh, PA (US);

Nedim Lipka, Campbell, CA (US);

Franck Dernoncourt, Spokane, WA (US);

Assignee:

Adobe Inc., San Jose, CA (US);

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06F 40/40 (2020.01); G06F 16/3329 (2025.01); G06N 3/0475 (2023.01); G06N 3/0895 (2023.01);
U.S. Cl.
CPC ...
G06F 40/40 (2020.01); G06N 3/0895 (2023.01);
Abstract

Methods and systems are provided for generating and using a unified fine-tuning dataset to fine-tune a language model. In embodiments described herein, a first labeled dataset having a first format of human feedback associated with performance of a pre-trained language model is accessed. Additionally, a second labeled dataset having a second format of human feedback associated with performance of the pre-trained language model is accessed. Thereafter, a unified fine-tuning dataset is generated by converting the second labeled dataset to a refined labeled dataset having the first format of human feedback and aggregating the first labeled dataset having the first format of human feedback with the refined labeled dataset having the first format of human feedback. The pre-trained language model is fine-tuned using the unified fine-tuning dataset and output for subsequent utilization.


Find Patent Forward Citations

Quick Actions:

Rossi, Ryan. (2026). Generation and utilization of unified fine-tuning datasets (U.S. Patent No. 12801862). U.S. Patent and Trademark Office. https://idiyas.com/patent/badge/12801862

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

Loading…