US 12,608,560 B2 · Custom-domain controller for large language models

Abstract

A database of text associated with different domains is maintained. Large language models (LLMs) are prepared for use in the different domains by providing the associated text to an instance of an LLM. Thus, using multiple instances of the same pre-trained LLM, domain-specific LLMs are generated. The text provided to the LLM instance may be selected based on an account identifier of the user accessing the LLM, the tenant accessing the LLM, a user selection of a domain, or any suitable combination thereof. A pool of prepared LLM instances may be generated before the access request is received. If a response provided by an LLM instance in a domain to a prompt was rejected by a user and additional information was received during the session to improve the response of the LLM instance, the additional information may be to the text used to prepare future LLM instances for the domain.

Claims20

Dependent claims

A system comprising:

a memory that stores instructions;
and
one or more processors coupled to the memory and configured to execute the instructions to perform operations comprising:
based on a domain for a session with a large language model (LLM), selecting a first set of input text from a database;
based on a tenant for the session with the LLM, selecting a second set of input text from the database;
providing the first set of input text to an instance of the LLM to prepare the LLM instance for the session;
providing the second set of input text to the instance of the LLM to further prepare the LLM instance for the session;
and
causing a user interface to be presented that allows a user to interact with the prepared LLM instance.

6 more elements

Dependencies are inferred from the claim text.

Custom-domain controller for large language models

Life of this patent

Custom-domain controller for large language models

Life of this patent

Abstract

Claims20