18401060. Resource-Efficient and Time-Efficient Prompting of a Language Model to Invoke Functions (Microsoft Technology Licensing, LLC)

Resource-Efficient and Time-Efficient Prompting of a Language Model to Invoke Functions

Organization Name

Microsoft Technology Licensing, LLC

Inventor(s)

Girish Milind Mahajan of Redmond WA US

Sayan Dev Pathak of Kirkland WA US

Michael Anthony Taylor of Kirkland WA US

Salman Mohammad Quazi of Mountain View CA US

Christopher Hakan Basoglu of Everett WA US

Prashanth Srikanthan of Seattle WA US

Resource-Efficient and Time-Efficient Prompting of a Language Model to Invoke Functions

This abstract first appeared for US patent application 18401060 titled 'Resource-Efficient and Time-Efficient Prompting of a Language Model to Invoke Functions

Original Abstract Submitted

A technique sends a first prompt to a language model that specifies selector information. The selector information provides a summary of a group of functions that are capable of being invoked. The language model responds by choosing one or more functions from the group of functions. The technique then sends a second prompt to the language model that specifies more detailed information regarding just the function(s) that have been identified by the language model. The language model responds by providing invocation information for each of the functions, such as properly formatted API messages. The technique then invokes the function(s) based on the invocation information. The technique reduces the size of each prompt sent to the language model, which makes efficient use of resources and improves the quality of the language model's output results.