公开(公告)号：US20250103300A1

公开(公告)日：2025-03-27

申请号：US18424372

申请日：2024-01-26

Applicant: Salesforce, Inc.

Inventor： Hung Le ,  Hailin Chen ,  Amrita Saha ,  Akash Gokul ,  Doyen Sahoo ,  Shafiq Rayhan Joty

IPC: G06F8/30 ,  G06F40/40

Abstract: The embodiments are directed to generating source code for a program from a problem description. One or more pre-trained code large language models (LLMs) generate sub-modules from a problem description in a natural language. The sub-modules are filtered based on testing criteria and encoded into sub-module encodings in an embedding space. The sub-module encodings are clustered into multiple clusters. A subset of sub-modules encoding that are close to the centroids of the clusters are selected. The sub-set of sub-modules is decoded into representative sub-modules. The problem description is augmented with the representative sub-modules and fed into one or more pre-trained code LLMs and new sub-modules are generated. The iterations continue until a program is generated from the representative sub-modules.

公开(公告)号：US12204857B2

公开(公告)日：2025-01-21

申请号：US18059234

申请日：2022-11-28

Applicant: Salesforce, Inc.

Inventor： Hailin Chen ,  Amrita Saha ,  Shafiq Rayhan Joty ,  Chu Hong Hoi

IPC: G06F40/284 ,  G06F18/214 ,  G06F18/2413 ,  G06F40/295 ,  G06F40/40

Abstract: Embodiments described herein provide training a prompt generator for text classification. A first training dataset associated with a first plurality of class labels is received for a first training process. For a first instance of the first training dataset, a set of labels of interest is generated by sampling from a set of possible class labels including the first plurality of class labels. The prompt generator generates a first prompt based on the set of labels of interest. A pretrained language model generates a task output in response to an input of the first instance prepended with the first prompt. A loss objective is generated based on the task output and the set of labels of interest. Parameters of the prompt generator are updated based on the computed loss function via backpropagation while the pretrained language model is frozen.

公开(公告)号：US20240249077A1

公开(公告)日：2024-07-25

申请号：US18316969

申请日：2023-05-12

Applicant: Salesforce, Inc.

Inventor： Hailin Chen ,  Shafiq Rayhan Joty ,  Amrita Saha ,  Chu Hong Hoi

IPC: G06F40/284 ,  G06N3/0455 ,  G06N3/084

CPC classification number: G06F40/284 ,  G06N3/0455 ,  G06N3/084

Abstract: Embodiments described herein provide a data driven framework that (i) translates demonstration examples to a fixed-length soft prompt—a sequence of soft tokens; and (ii) learns a global (not generated from demonstrations) soft prompt. The framework then combines the global prompt, the translated prompts and the original context to create an augmented context which is given as final input for the backbone LM to use.

公开(公告)号：US20240428079A1

公开(公告)日：2024-12-26

申请号：US18499101

申请日：2023-10-31

Applicant: Salesforce, Inc.

Inventor： Hailin Chen ,  Amrita Saha ,  Chu Hong (Steven) Hoi ,  Shafiq Rayhan Joty

IPC: G06N3/09

Abstract: Embodiments described herein provide a system for training a neural network model using a teacher-student framework. The system includes a communication interface configured to communicate with a teacher model; a memory storing a student model and a plurality of processor-executable instructions; and a processor executing the processor-executable instructions to perform operations. The operations include: generating, by the student model, a first task output in response to a task input; obtaining, from an evaluation environment, a feedback relating to an accuracy of the first task output; obtaining a refinement output generated by the teacher model based on an input of the first task output and the feedback; and training the student model based on a training input of the first task output and the feedback and a training label of the refinement output.