Prompt Tuning Using One or More Machine-Learned Models

    公开(公告)号:US20240378196A1

    公开(公告)日:2024-11-14

    申请号:US18684518

    申请日:2021-08-20

    Applicant: Google LLC

    Abstract: Systems and methods for prompt tuning can leverage semantic searching for determining similar prompts to use for retraining. A prompt can be generated then searched to find the similar prompts. Data related to the similar prompts can then be utilized for prompt tuning. Moreover, systems and methods for prompt tuning can generate and utilize a meta-prompt to reduce the computational cost of generating prompts. The prompt tuning techniques can be implemented as part of a prompt tuning application programming interface (API).

Patent Agency Ranking