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. 28, 2026

Filed:

Jan. 31, 2025
Applicant:

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

Inventors:

Fan Yin, Palo Alto, CA (US);

Xiangyu Peng, Palo Alto, CA (US);

Philippe Laban, New York, NY (US);

Yilun Zhou, New York, NY (US);

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

Assignee:

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

Attorney:
Primary Examiner:
Int. Cl.
CPC ...
G06F 16/335 (2019.01); G06F 16/353 (2025.01); G06N 3/08 (2023.01);
U.S. Cl.
CPC ...
G06F 16/335 (2019.01); G06F 16/353 (2019.01); G06N 3/08 (2013.01);
Abstract

In view of the potential misuse of AI to disseminate dangerous knowledge, embodiments described herein provide an AI safety training framework with a data generation pipeline for generating datasets indicative of multiple different severity levels of potentially harmful LLM-generated text to identify and respond to a potentially harmful query, and/or moderate a potentially harmful LLM-generated text. In this way, an LLM moderator may be integrated as a safety layer within an AI system's architecture, acting as a 'firewall' to filter responses generated by another AI chat engine.


Find Patent Forward Citations

Loading…