Self-adjusting assistant LLMs enabling robust interaction with business LLMs
AssigneeGoogle Inc.
InventorsVictor Carbune, Matthew Sharifi
Life of this patent
Estimating the term…
Loading patent…
AssigneeGoogle Inc.
InventorsVictor Carbune, Matthew Sharifi
Estimating the term…
A method includes receiving a natural language query specifying an action for an assistant interface to perform and selecting one or more business large language models (LLMs) for the assistant interface to interact with to fulfill performance of the action. For each business LLM, method also includes accessing an adapter module to structure the natural language query into a respective prompt specifically formulated for the corresponding business LLM, issuing, for input to the corresponding business LLM, the respective prompt, and receiving corresponding response content from the corresponding business LLM that conveys details regarding performance of a corresponding portion of the action. The method also includes presenting, for output from the user device, presentation content based on the corresponding response content received from each corresponding business LLM.
A computer-implemented method executing on data processing hardware that causes the data processing hardware to perform operations comprising:
A system comprising:
Dependencies are inferred from the claim text.