公开(公告)号：US20230083512A1

公开(公告)日：2023-03-16

申请号：US17588043

申请日：2022-01-28

Applicant: salesforce.com, inc.

Inventor： Benjamin Newman ,  Nazneen Rajani ,  Prafulla Kumar Choubey

IPC: G06F40/279 ,  G06F40/126 ,  G06N3/04

Abstract: Embodiments described herein provide a system and method for extracting factual information. The system transforms a query into a natural language prompt in a format of a query subject and a queried relation. The system encodes, via an embedding layer of a pre-trained language model, the natural language prompt into a first embedding. The system encodes, via the adapter model, the first embedding into a second embedding based on a probability that the second embedding returns the factual information when the second embedding is fed the first attention layer of the pre-trained language model. The system decodes, by the first attention layer of the pre-trained language mode, the second embedding into a response to the query. The system extracts the factual information from the decoded response to the query.

公开(公告)号：US20230119109A1

公开(公告)日：2023-04-20

申请号：US17586467

申请日：2022-01-27

Applicant: salesforce.com, inc.

Inventor： Prafulla Kumar Choubey ,  Nazneen Rajani

IPC: G06N20/20 ,  G06K9/62 ,  G06F40/284

Abstract: Embodiments described herein provide a document summarization framework that controls different factual errors, referred to as “Mixture of Factual Experts (MoFE)” framework. MoFE applies an ensemble of factual expert models to control hallucination in summarization systems. Each factual expert model is trained to generate summaries with a unique type of factual quality. Factual consistency metrics may be used to filter training data in order to adjust the training inputs for each respective expert. The overall factual quality of MoFE may be achieved by controlling the relative weight of each factual expert. The experts may be ensembled (either through logits ensembling, or weighted average of parameters) in order to create a combined output that shares characteristics from each according to its relative weight.