Patent · US Active

Transparent and controllable human-AI interaction via chaining of machine-learned language models

US12141556B2 · kind B2 · utility

0Cited by

1References

20Claims

0Family size

Assignee

Google LLC · US

Inventors

Carrie Cai · Mountain View, US
Tongshuang Wu · Seattle, US
Michael Andrew Terry · Cambridge, US

Key dates

Filing date	Sep 30, 2022
Grant date	Nov 12, 2024
Priority date	—
Expiry date	Oct 17, 2042

Classification

Technology area (CPC G)Physics
CPC primaryG06F8/34
WIPO fieldComputer technology
WIPO sectorElectrical engineering

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.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.