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.:
Date of Patent:
Nov. 17, 2026
Filed:
Jul. 30, 2024
Google Llc, Mountain View, CA (US);
Jinhyuk Lee, Sunnyvale, CA (US);
Zhuyun Dai, Sunnyvale, CA (US);
Xiaoqi Ren, Kirkland, WA (US);
Iftekhar Naim, Los Gatos, CA (US);
Yi Luan, Kirkland, WA (US);
Blair Yuxin Chen, San Jose, CA (US);
Siddhartha Reddy Jonnalagadda, Sunnyvale, CA (US);
Ming-Wei Chang, Redmond, WA (US);
Daniel Matthew Cer, Santa Clara, CA (US);
Gustavo Adolfo Hernandez Abrego, Mountain View, CA (US);
Jeremy Robert Cole, San Francisco, CA (US);
Colin Hearne Evans, San Mateo, CA (US);
Yuzhe Zhao, San Francisco, CA (US);
Pranay Bhatia, Palo Alto, CA (US);
Rajvi Kapadia, Sunnyvale, CA (US);
Riham Hassan Abdel-Moneim Mansour, Kirkland, WA (US);
Raphael Dominik Hoffman, Los Altos, CA (US);
Simon Kunio Tokumine, San Francisco, CA (US);
Scott Bradley Huffman, Portola Valley, CA (US);
Stephen Zachary Karukas, Seattle, WA (US);
Michael Yiupun Kwong, San Jose, CA (US);
Shu Zheng, Bellevue, CA (US);
Yan Qiao, Millbrae, CA (US);
Lukas Rutishauser, Kirkland, CA (US);
Anand Rajan Iyer, Sunnyvale, CA (US);
Google LLC, Mountain View, CA (US);
Abstract
An example method includes providing, to a sequence model (i) a plurality of few-shot prompts, wherein each prompt comprises a demonstration passage, a demonstration task, and a demonstration query, wherein the demonstration task describes a type of retrieval, and wherein the demonstration query is relevant to the demonstration task, and (ii) a plurality of passages sampled from a corpus of passages. The method also includes receiving, from the sequence model and for the plurality of passages and based on the plurality of few-shot prompts, a respective plurality of predicted task-query pairs, the sequence model having been prompted to predict a task based on an input passage, and predict an output query relevant to the predicted task. The method further includes generating a synthetic training dataset comprising the plurality of passages and the respective plurality of predicted task-query pairs. The method also includes providing the synthetic training dataset.
Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile