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:
Jul. 15, 2025

Filed:

Aug. 03, 2022
Applicant:

Salesforce, Inc., San Francisco, CA (US);

Inventors:

Prafulla Kumar Choubey, San Jose, CA (US);

Alexander R. Fabbri, San Francisco, CA (US);

Jesse Vig, Los Altos, CA (US);

Chien-Sheng Wu, Mountain View, CA (US);

Wenhao Liu, Redwood City, CA (US);

Nazneen Rajani, Mountain View, CA (US);

Assignee:

Salesforce, Inc., San Francisco, CA (US);

Attorney:
Primary Examiner:
Assistant Examiner:
Int. Cl.
CPC ...
G06F 40/166 (2020.01); G06N 20/00 (2019.01);
U.S. Cl.
CPC ...
G06F 40/166 (2020.01); G06N 20/00 (2019.01);
Abstract

Embodiments described herein provide a document summarization framework that employs an ensemble of summarization models, each of which is a modified version of a base summarization model to control hallucination. For example, a base summarization model may first be trained on a full training data set. The trained base summarization model is then fine-tuned using a first filtered subset of the training data which contains noisy data, resulting in an 'anti-expert' model. The parameters of the anti-expert model are subtracted from the parameters of the trained base model to produce a final summarization model which yields robust factual performance.


Find Patent Forward Citations

Loading…