Jump to content

QUALCOMM Incorporated (20250131121). Privacy Enhanced Language Model Prompt

From WikiPatents
Revision as of 17:34, 24 April 2025 by Wikipatents (talk | contribs) (Creating a new page)
(diff) ← Older revision | Latest revision (diff) | Newer revision → (diff)

Privacy Enhanced Language Model Prompt

Organization Name

QUALCOMM Incorporated

Inventor(s)

Diyan Teng of Sunnyvale CA US

Mehul Soman of San Jose CA US

Junsheng Han of Los Altos Hills CA US

Nauman Shahid of Cork IE

Rashmi Kulkarni of Redwood City CA US

Justin Mcgloin of Los Altos CA US

Brian Momeyer of Escondido CA US

Privacy Enhanced Language Model Prompt

This abstract first appeared for US patent application 20250131121 titled 'Privacy Enhanced Language Model Prompt

Original Abstract Submitted

various embodiments include systems and methods for generating a prompt for a large generative ai model (lxm). a computing device may be configured to receive a user prompt, process the received user prompt to recognize whether the prompt includes privacy information or will cause an lxm to provide a response that will reveal privacy information; and use the lxm to provide a response to the user prompt in a manner that will avoid disclosure of privacy information.

Cookies help us deliver our services. By using our services, you agree to our use of cookies.