公开(公告)号：US20250045316A1

公开(公告)日：2025-02-06

申请号：US18788178

申请日：2024-07-30

Applicant: Google LLC

Inventor： Jinhyuk Lee ,  Zhuyun Dai ,  Xiaoqi Ren ,  Iftekhar Naim ,  Yi Luan ,  Blair Yuxin Chen ,  Siddhartha Reddy Jonnalagadda ,  Ming-Wei Chang ,  Daniel Matthew Cer ,  Gustavo Adolfo Hernandez Abrego ,  Jeremy Robert Cole ,  Colin Hearne Evans ,  Yuzhe Zhao ,  Pranay Bhatia ,  Rajvi Kapadia ,  Riham Hassan Abdel-Moneim Mansour ,  Raphael Dominik Hoffman ,  Simon Kunio Tokumine ,  Scott Bradley Huffman ,  Stephen Zachary Karukas ,  Michael Yiupun Kwong ,  Shu Zheng ,  Yan Qiao ,  Lukas Rutishauser ,  Anand Rajan Iyer

IPC: G06F16/33 ,  G06N3/08

Abstract: An example method includes providing, to a sequence model (i) a plurality of few-shot prompts, wherein each prompt comprises a demonstration passage, a demonstration task, and a demonstration query, wherein the demonstration task describes a type of retrieval, and wherein the demonstration query is relevant to the demonstration task, and (ii) a plurality of passages sampled from a corpus of passages. The method also includes receiving, from the sequence model and for the plurality of passages and based on the plurality of few-shot prompts, a respective plurality of predicted task-query pairs, the sequence model having been prompted to predict a task based on an input passage, and predict an output query relevant to the predicted task. The method further includes generating a synthetic training dataset comprising the plurality of passages and the respective plurality of predicted task-query pairs. The method also includes providing the synthetic training dataset.

公开(公告)号：US20240232637A9

公开(公告)日：2024-07-11

申请号：US18491877

申请日：2023-10-23

Applicant: Google LLC

Inventor： Krishna Pragash Srinivasan ,  Michael Bendersky ,  Anupam Samanta ,  Lingrui Liao ,  Luca Bertelli ,  Ming-Wei Chang ,  Iftekhar Naim ,  Siddhartha Brahma ,  Siamak Shakeri ,  Hongkun Yu ,  John Nham ,  Karthik Raman ,  Raphael Dominik Hoffmann

IPC: G06N3/0895 ,  G06F16/903 ,  G06F16/93 ,  G06N3/0455

CPC classification number: G06N3/0895 ,  G06F16/90335 ,  G06F16/93 ,  G06N3/0455

Abstract: Provided are computing systems, methods, and platforms that train query processing models, such as large language models, to perform query intent classification tasks by using retrieval augmentation and multi-stage distillation. Unlabeled training examples of queries may be obtained, and a set of the training examples may be augmented with additional feature annotations to generate augmented training examples. A first query processing model may annotate the retrieval augmented queries to generate inferred labels for the augmented training examples. A second query processing model may be trained on the inferred labels, distilling the query processing model that was trained with retrieval augmentation into a non-retrieval augmented query processing model. The second query processing model may annotate the entire set of unlabeled training examples. Another stage of distillation may train a third query processing model using the entire set of unlabeled training examples without retrieval augmentation.

公开(公告)号：US20240135187A1

公开(公告)日：2024-04-25

申请号：US18491877

申请日：2023-10-22

Applicant: Google LLC

Inventor： Krishna Pragash Srinivasan ,  Michael Bendersky ,  Anupam Samanta ,  Lingrui Liao ,  Luca Bertelli ,  Ming-Wei Chang ,  Iftekhar Naim ,  Siddhartha Brahma ,  Siamak Shakeri ,  Hongkun Yu ,  John Nham ,  Karthik Raman ,  Raphael Dominik Hoffmann

IPC: G06N3/0895 ,  G06F16/903 ,  G06F16/93 ,  G06N3/0455

CPC classification number: G06N3/0895 ,  G06F16/90335 ,  G06F16/93 ,  G06N3/0455

Abstract: Provided are computing systems, methods, and platforms that train query processing models, such as large language models, to perform query intent classification tasks by using retrieval augmentation and multi-stage distillation. Unlabeled training examples of queries may be obtained, and a set of the training examples may be augmented with additional feature annotations to generate augmented training examples. A first query processing model may annotate the retrieval augmented queries to generate inferred labels for the augmented training examples. A second query processing model may be trained on the inferred labels, distilling the query processing model that was trained with retrieval augmentation into a non-retrieval augmented query processing model. The second query processing model may annotate the entire set of unlabeled training examples. Another stage of distillation may train a third query processing model using the entire set of unlabeled training examples without retrieval augmentation.

公开(公告)号：US20250086434A1

公开(公告)日：2025-03-13

申请号：US18824530

申请日：2024-09-04

Applicant: Google LLC

Inventor： Dorothea Wiesmann Rothuizen ,  Vincent Leroy ,  Sai Meher Karthik Duddu ,  Raphael Dominik Hoffmann ,  Dan Beat Kluser ,  Iftekhar Naim

IPC: G06N3/0455

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for enabling artificial intelligence (AI) to evaluate attributes of items and use the results of the evaluation to provide relevant content. In one aspect, a method includes receiving, by an AI system and from a client device of a user, a first query of a user session. For each additional query, the AI system generates input data based on the additional query and data related to one or more previous queries received during the user session. The AI system provides the input data as an input to a machine learning model trained to output attributes of items and importance data indicating a relative importance of the attributes based on received inputs. The AI system selects one or more digital components based on the set of attributes and the importance data output by the model.