Model capability extraction
The indirect querying of models to determine capabilities possessed by the model. Such indirect queries take the form of model input that potentially includes a natural language input user data. Such model input is structured such that the output of the model is either not natural language at all, or else is natural language that is not semantically responsive to the natural language input. Nevertheless, the output is evaluated to estimate or determine the capability possessed by the model. Thus, models may be more fully utilized to their better potential.
1 . A computing system that determines a capability of a language model without directly querying the language model to ask what capabilities the language model has, said computing system comprising:
a capability extraction system that interacts with the language model to determine the capability of the language model, wherein the capability extraction system interacts with the language model by (i) providing language model input to the language model, (ii) receiving resulting output from the language model, and (iii) evaluating the output to identify the capability of the language model;
a model utilization system that receives a capability indication from the capability extraction system, where the capability indication indicates the capability of the language model, and that utilizes the capability of the language model by tasking the language model to assist in performing an operation;
one or more processors; and
one or more hardware storage devices that store instructions that are executable by the one or more processors to cause the computing system to:
causing the capability extraction system to formulate the language model input, wherein the capability extraction system structures the language model input to include natural language input;
causing the capability extraction system to feed the language model input to the language model;
causing the capability extraction system to access the output from the language model, where the output results from the language model input being provided to the language model, the output being in a form of a non-natural language output or a natural language output that is semantically non-responsive to the natural language input;
causing the capability extraction system to output a capability indication indicating an estimation or determination of the capability of the language model, wherein the capability indication is generated based on the output from the language model;
causing the capability extraction system to provide the capability indication and the output from the language model to the model utilization system;
as a part of a first operation of the model utilization system, causing the model utilization system to use the output, which is an earlier generated output, to perform the first operation, such that the model utilization system does not engage with the language model during the first operation; and
as a part of a second operation of the model utilization system, causing the model utilization system to utilize the capability of the language model by tasking the language model to assist in performing the second operation, such that the model utilization system does engage with the language model during the second operation,
wherein the language model is a large language model.
2 . The computing system in accordance with claim 1 , wherein the natural language input includes a natural language request to perform a task, and wherein the output includes a result of the language model performing the task.
3 . The computing system in accordance with claim 1 , wherein the output is code.
4 . The computing system in accordance with claim 1 , wherein the output is a generated image.
5 . The computing system in accordance with claim 1 , the capability being a capability to semantically determine a type of a string provided in the language model input.
6 . The computing system in accordance with claim 1 , the capability comprising a support of the language model for abbreviations.
7 . The computing system in accordance with claim 1 , the capability comprising a capability to determine how components of data within the language model input are related.
8 . The computing system in accordance with claim 1 , the capability comprising a recognition of an importance of data within the language model input.
9 . The computing system in accordance with claim 1 , the capability comprising an awareness of a property of data within the language model input.
10 . The computing system in accordance with claim 1 , wherein the capability is used by a compiler to perform compilation.
11 . The computing system in accordance with claim 1 , wherein the capability is used to automatically make a suggestion about data to a user.
12 . A method for determining a capability of a language model without directly querying the language model to ask what capabilities the language model has, said method comprising:
accessing a capability extraction system that interacts with the language model to determine the capability of the language model, wherein the capability extraction system interacts with the language model by (i) providing language model input to the language model, (ii) receiving resulting output from the language model, and (iii) evaluating the output to identify the capability of the language model;
accessing a model utilization system that receives a capability indication from the capability extraction system, where the capability indication indicates the capability of the language model, and that utilizes the capability of the language model by tasking the language model to assist in performing an operation;
causing the capability extraction system to formulate the language model input, wherein the capability extraction system structures the language model input to include natural language input;
causing the capability extraction system to feed the language model input to the language model;
causing the capability extraction system to access the output from the language model, where the output results from the language model input being provided to the language model, the output being in a form of a non-natural language output or a natural language output that is semantically non-responsive to the natural language input;
causing the capability extraction system to output a capability indication indicating an estimation or determination of the capability of the language model, wherein the capability indication is generated based on the output from the language model;
causing the capability extraction system to provide the capability indication and the output from the language model to the model utilization system;
as a part of a first operation of the model utilization system, causing the model utilization system to use the output, which is an earlier generated output, to perform the first operation, such that the model utilization system does not engage with the language model during the first operation; and
as a part of a second operation of the model utilization system, causing the model utilization system to utilize the capability of the language model by tasking the language model to assist in performing the second operation, such that the model utilization system does engage with the language model during the second operation,
wherein the language model is a large language model.