USING SAMPLE QUESTION EMBEDDINGS TO CHOOSE BETWEEN AN LLM INTERFACING MODEL AND A NON-LLM INTERFACING MODEL

    公开(公告)号:US20240362213A1

    公开(公告)日:2024-10-31

    申请号:US18398058

    申请日:2023-12-27

    Applicant: Box, Inc.

    CPC classification number: G06F16/24522 G06F16/22 G06F16/24573 G06F40/40

    Abstract: Methods, systems, and computer program products for managing interactions between a content management system (CMS) and a large language model (LLM) system. The semantics of user questions can be considered before prompting an LLM, or alternatively, before querying datasets that are local to the CMS. Given a user question to be answered, the embedding of the user question can be matched against preconfigured sample question embeddings to determine a best match. A prompt corresponding to the determined best match is then configured based on identification of the class or classes that correspond to the matched question. Prompts for provision to LLMs can be synthesized based on a particular user's identity and/or based on the particular user's historical collaboration activities over objects of the CMS. The LLM can be hosted by a third-party provider. Alternatively all or portions of a large language model system can be hosted within the CMS.

    CHOOSING A LARGE LANGUAGE MODEL INTERFACING MECHANISM BASED ON SAMPLE QUESTION EMBEDDINGS

    公开(公告)号:US20240362497A1

    公开(公告)日:2024-10-31

    申请号:US18398039

    申请日:2023-12-27

    Applicant: Box, Inc.

    CPC classification number: G06N5/01 G06N3/0455

    Abstract: Methods, systems, and computer program products for managing interactions between a content management system (CMS) and a large language model (LLM) system. The semantics of user questions can be considered before prompting an LLM, or alternatively, before querying datasets that are local to the CMS. Given a user question to be answered, the embedding of the user question can be matched against preconfigured sample question embeddings to determine a best match. A prompt corresponding to the determined best match is then configured based on identification of the class or classes that correspond to the matched question. Prompts for provision to LLMs can be synthesized based on a particular user's identity and/or based on the particular user's historical collaboration activities over objects of the CMS. The LLM can be hosted by a third-party provider. Alternatively all or portions of a large language model system can be hosted within the CMS.

    GENERATING A LARGE LANGUAGE MODEL PROMPT BASED ON COLLABORATION ACTIVITIES OF A USER

    公开(公告)号:US20240362476A1

    公开(公告)日:2024-10-31

    申请号:US18398050

    申请日:2023-12-27

    Applicant: Box, Inc.

    CPC classification number: G06N3/08

    Abstract: Methods, systems, and computer program products for managing interactions between a content management system (CMS) and a large language model (LLM) system. The semantics of user questions can be considered before prompting an LLM, or alternatively, before querying datasets that are local to the CMS. Given a user question to be answered, the embedding of the user question can be matched against preconfigured sample question embeddings to determine a best match. A prompt corresponding to the determined best match is then configured based on identification of the class or classes that correspond to the matched question. Prompts for provision to LLMs can be synthesized based on a particular user's identity and/or based on the particular user's historical collaboration activities over objects of the CMS. The LLM can be hosted by a third-party provider. Alternatively all or portions of a large language model system can be hosted within the CMS.

Patent Agency Ranking