Large-Scale, Privacy Preserving Personalized Large Language Models (LLMs)
AssigneeGoogle Inc.
InventorsMichael Bendersky, Mingyang Zhang
Life of this patent
Estimating the term…
Abstract
A method for providing personalized responses to textual prompts using a large scale, privacy preserving, large language model (LLM) includes receiving a textual prompt from a user specifying a task for an LLM to perform, and obtaining a set of user features associated with the user. The method also includes determining, using the set of user features associated with the user, a user prompt embedding for the user, and processing, using the LLM, the textual prompt conditioned on the user prompt embedding for the user to generate a personalized response to the textual prompt. The method further includes providing the personalized response to the textual prompt for output from a user device associated with the user.
Claims28
A computer-implemented method that when executed on data processing hardware causes the data processing hardware to perform operations comprising:
- receiving a textual prompt from a user specifying a task for a large language model (LLM) to perform;
- obtaining a set of user features associated with the user;
- determining, using the set of user features associated with the user, a user prompt embedding for the user;
- processing, using the LLM, the textual prompt conditioned on the user prompt embedding for the user to generate a personalized response to the textual prompt;
- and
- providing the personalized response to the textual prompt for output from a user device associated with the user.
A system comprising:
- data processing hardware;
- and
- memory hardware in communication with the data processing hardware, the memory hardware storing instructions that when executed on the data processing hardware cause the data processing hardware to perform operations comprising:
- receiving a textual prompt from a user specifying a task for a large language model (LLM) to perform;
- obtaining a set of user features associated with the user;
- determining, using the set of user features associated with the user, a user prompt embedding for the user;
- processing, using the LLM, the textual prompt conditioned on the user prompt embedding for the user to generate a personalized response to the textual prompt;
- and
- providing the personalized response to the textual prompt for output from a user device associated with the user.
Dependencies are inferred from the claim text.