Back to results
US 12,754,914 B2Granted
Polling and serial prompting for traversal of multiple specialist language models
AssigneeInsight Direct USA, Inc.
InventorScott Joynt
Life of this patent
Estimating the term…
Abstract
A method of processing a compound prompt using a plurality of specialized large language models (LLMs) includes decomposing the compound prompt into a plan with multiple steps. For each step, an approach defining a subset of the specialized LLMs is selected and executed to produce multiple model outputs, and these model outputs are collectively used to generate a step output. The step outputs associated with each step are assembled into a syntactically and semantically coherent final output via an integration module utilizing a large language model.
Claims19
A method of processing a compound prompt using a plurality of specialized large language models (LLMs), the method comprising:
- training a plurality of language models (LMs) including an integration module LM and a plurality of specialized LLMs, wherein:
- each of the plurality of LMs is trained using training data different from all others of the plurality of LMs;
- and
- each of the plurality of specialized LLMs corresponds to a specific specialist domain, and is trained at least partly using training data specific to its respective specialist domain;
- decomposing the compound prompt into a plan having a plurality of steps via a planner module instantiated in machine-readable memory and operable by a processor;
- and
- for each of the plurality of steps:
- selecting an approach for producing a step output using a selection module, the approach defining a subset of the plurality of specialized LLMs;
- generating model outputs based on the step from each of the subset of the plurality of specialized LLMs;
- and
- generating, from the model outputs generated by each of the subset of the plurality of specialized LLMs, a step output responsive to the step,
- wherein for at least one of the plurality of steps, the approach specifies receiving a model output from pass-forward serially chained calls of each of the subset of the plurality of specialized LLMs, beginning with a model input based on the respective step, and
- wherein receiving a final model output from pass-forward serially chained calls of each of the subset of the plurality of specialized LLMs comprises traversing multiple permutations of serial orders of the step-specific subset of the plurality of LLMs;
- and
- assembling all of the step outputs into a syntactically and semantically coherent final output via an integration module utilizing the integration module LM.
12 more elements
A system for generating a response to a complex prompt, the system comprising:
- an input device configured to receive the complex prompt;
- a logic processor;
- machine-readable memory;
- a plurality of language models (LMs) instantiated in the machine-readable
- memory and comprising:
- an integration module LM;
- and
- a plurality of specialized large language models (LLMs) each having a corresponding domain of specialization;
- wherein each of the plurality of LMs is trained using training data different from all others of the plurality of LMs, and each of the plurality of specialized LLMs is trained at least partly using training data specific to its respective specialist domain;
- and
- a manager comprising:
- a planner instantiated in the machine-readable memory and operable via the logic processor to decompose the complex prompt into a plan having a plurality of steps;
- a selection module instantiated in the machine-readable memory and operable via the logic processor, for each of the plurality of steps, to identify an approach for defining a step-specific subset of the plurality of specialized LLMs, and for generating a single step output corresponding to that step using outputs from each of step-specific subset of the plurality of specialized LLMs;
- and
- an integration module instantiated in the machine-readable memory and operable via the logic processor to generate a language output responsive to the complex prompt from all of the step outputs corresponding to each of the plurality of steps;
- wherein for at least one of the plurality of steps, the approach specifies receiving a model output from pass-forward serially chained calls of each of the step-specific subset of the plurality of specialized LLMs, beginning with a model input based on the respective step, and
- wherein receiving a final model output from pass-forward serially chained calls of each of the step-specific subset of the plurality of specialized LLMs comprises traversing multiple permutations of serial orders of the step-specific subset of the plurality of LLMs.
14 more elements
Dependencies are inferred from the claim text.