公开(公告)号：US20250111151A1

公开(公告)日：2025-04-03

申请号：US18477209

申请日：2023-09-28

Applicant: Amazon Technologies, Inc.

Inventor： Zhiheng Huang ,  Yue Yang ,  Lan Liu

IPC: G06F40/205 ,  G06F40/284 ,  G06N3/0455

Abstract: An index is created with split documents to retrieve and augment generation of a response to a natural language request using a generative machine learning model. When a natural language request is received, a search representation is generated and used to retrieve candidate portions of documents from the index. A relevancy ranking is performed to identify relevant portions of documents from the candidates and provide the relevant portions to prompt a generative machine learning model to provide a result for the natural language request.

公开(公告)号：US20250111267A1

公开(公告)日：2025-04-03

申请号：US18478811

申请日：2023-09-29

Applicant: Amazon Technologies, Inc.

Inventor： Zhiheng Huang ,  Yue Yang ,  Lan Liu ,  Yuhao Zhang ,  Peng Qi

IPC: G06N20/00 ,  G06F40/30 ,  G06F40/40

Abstract: Template-based tuning is performed on a generative machine learning model where a shared template is used to tune the generative machine learning model across multiple natural language tasks. When a natural language request to perform a natural language task is received, portions of a shared template to complete are identified as part of generating a prompt. The generative machine learning model is instructed according to the generated prompt and a response to the request is returned based on a result of the generative machine learning model.