公开(公告)号：US20230112921A1

公开(公告)日：2023-04-13

申请号：US17957526

申请日：2022-09-30

Applicant: Google LLC

Inventor： Carrie Cai ,  Tongshuang Wu ,  Michael Andrew Terry

IPC: G06F8/35 ,  G06F8/30 ,  G06F8/34

Abstract: The present disclosure provides to transparent and controllable human-AI interaction via chaining of machine-learned language models. In particular, although existing language models (e.g., so-called “large language models” (LLMs)) have demonstrated impressive potential on simple tasks, their breadth of scope, lack of transparency, and insufficient controllability can make them less effective when assisting humans on more complex tasks. In response, the present disclosure introduces the concept of chaining instantiations of machine-learned language models (e.g., LLMs) together, where the output of one instantiation becomes the input for the next, and so on, thus aggregating the gains per step.

公开(公告)号：US20250036376A1

公开(公告)日：2025-01-30

申请号：US18915020

申请日：2024-10-14

Applicant: Google LLC

Inventor： Carrie Cai ,  Tongshuang Wu ,  Michael Andrew Terry

IPC: G06F8/35 ,  G06F8/30 ,  G06F8/34

Abstract: The present disclosure provides to transparent and controllable human-AI interaction via chaining of machine-learned language models. In particular, although existing language models (e.g., so-called “large language models” (LLMs)) have demonstrated impressive potential on simple tasks, their breadth of scope, lack of transparency, and insufficient controllability can make them less effective when assisting humans on more complex tasks. In response, the present disclosure introduces the concept of chaining instantiations of machine-learned language models (e.g., LLMs) together, where the output of one instantiation becomes the input for the next, and so on, thus aggregating the gains per step.

公开(公告)号：US12141556B2

公开(公告)日：2024-11-12

申请号：US17957526

申请日：2022-09-30

Applicant: Google LLC

Inventor： Carrie Cai ,  Tongshuang Wu ,  Michael Andrew Terry

IPC: G06F8/35 ,  G06F8/30 ,  G06F8/34

Abstract: The present disclosure provides to transparent and controllable human-AI interaction via chaining of machine-learned language models. In particular, although existing language models (e.g., so-called “large language models” (LLMs)) have demonstrated impressive potential on simple tasks, their breadth of scope, lack of transparency, and insufficient controllability can make them less effective when assisting humans on more complex tasks. In response, the present disclosure introduces the concept of chaining instantiations of machine-learned language models (e.g., LLMs) together, where the output of one instantiation becomes the input for the next, and so on, thus aggregating the gains per step.