Prompt Tuning Pipeline
AssigneeServiceNow, Inc.
InventorsDariush Shahgoshtasbi, Gaurav Goyal, Tao Feng
Life of this patent
Estimating the term…
Loading patent…
AssigneeServiceNow, Inc.
InventorsDariush Shahgoshtasbi, Gaurav Goyal, Tao Feng
Estimating the term…
Embodiments are provided to distill the knowledge of a large model with respect to a tasks into a prompt that can be applied to a smaller model in order to improve the smaller model's performance of the task. This is accomplished by generating, by the large model, a set of queries and associated prompt segments related to sub-tasks, background knowledge, or other information about the tasks that may not be represented adequately by the smaller model. The smaller model's responses to the queries are assessed and, if found to represent reduced competence, the corresponding prompt segment is added to a model-specific prompt. The model-specific prompt is thus selectively expanded to include prompt segments that compensate for incompetencies of the smaller model with respect to corresponding aspects (e.g., sub-tasks) of the task instructed by the prompt.
A method comprising:
A method comprising:
A non-transitory computer-readable medium, having stored thereon program instructions that, upon execution by a computing system, cause the computing system to perform operations comprising:
Dependencies are inferred from the claim text.