公开(公告)号：US20250111157A1

公开(公告)日：2025-04-03

申请号：US18900500

申请日：2024-09-27

Applicant: Google LLC

Inventor： Guy Tennenholtz ,  Yinlam Chow ,  Chih-wei Hsu ,  Jihwan Jeong ,  Lior Shani ,  Deepak Ramachandran ,  Martin Mirolyubov Mladenov ,  Craig Edgar Boutilier

IPC: G06F40/284 ,  G06F40/40 ,  G06N3/0455

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for analyzing embedding spaces using large language models. In one aspect, a method performed by one or more computers for analyzing a target embedding space using a neural network configured to perform a set of machine learning tasks is described. The method includes: obtaining, for each of one or more entities, a respective domain embedding representing the entity in the target embedding space; receiving a text prompt including a sequence of input tokens describing a particular machine learning task in the set to be performed on the one or more entities; preparing, for the neural network, an input sequence including each input token in the text prompt and each domain embedding; and processing the input sequence, using the neural network, to generate a sequence of output tokens describing a result of the particular machine learning task.