公开(公告)号：US20240428783A1

公开(公告)日：2024-12-26

申请号：US18341412

申请日：2023-06-26

Applicant: Amazon Technologies, Inc.

Inventor： Rahul Gupta ,  Charith Peris ,  Palash Goyal ,  Lisa Bauer ,  Ninareh Mehrabi

IPC: G10L15/18 ,  G10L15/26

Abstract: Systems and techniques for moderating responses of a generative language model are described herein. Some user inputs to a generative language model may include biases, misinformation, and other references to moderated content. To prevent the generative language model from generating responses that promote these forms of moderated content, the techniques described determine a policy corresponding to the determined moderated content category of the user input. The determined policy may correspond to a template of instructions for how the generative language model is to respond to such moderated content. The output of the generative language model may also be moderated before being presented to the user.

公开(公告)号：US20240420453A1

公开(公告)日：2024-12-19

申请号：US18216271

申请日：2023-06-29

Applicant: Amazon Technologies, Inc.

Inventor： Rahul Gupta ,  Ninareh Mehrabi ,  Palash Goyal ,  Kai-Wei Chang ,  Aram Galstyan

IPC: G06V10/772 ,  G06F40/30 ,  G06F40/40 ,  G06V10/774

Abstract: Techniques for generating synthetic data for machine learning (ML) models are described. A system includes a language model that processes a task and a corresponding set of example inputs to generate another input, referred to herein as a machine-generated data. The machine-generated data is processed using a ML, model (that data is being generated for) to determine a model output, and the model output is analyzed to determine whether it corresponds to a target output. If the model output corresponds to the target output, then the machine-generated data is added to the set of example inputs and one of the original example inputs is removed to generate an updated set of example inputs. The updated set can be used for various training techniques.