公开(公告)号：US20250094456A1

公开(公告)日：2025-03-20

申请号：US18887751

申请日：2024-09-17

Applicant: GOOGLE LLC

Inventor： Kelvin Gu ,  Zhuyun Dai ,  Panupong Pasupat ,  Chen Elkind ,  Eran Ofek ,  Hagai Taitelbaum ,  Mukund Sundararajan ,  Vered Cohen ,  Itay Karo ,  Norbert Kalb ,  Yossi Matias ,  Tej Toor ,  Teghan Tracy

IPC: G06F16/332 ,  G06F16/33 ,  G06F16/35

Abstract: Implementations are described herein for identifying potentially false information in generative model output by performing entailment evaluation of generative model output. In various implementations, data indicative of a query may be processed to generate generative model output. Textual fragments may be extracted from the generative model output, and a subset of the textual fragments may be classified as being suitable for textual entailment analysis. Textual entailment analysis may be performed on each textual fragment of the subset, including formulating a search query based on the textual fragment, retrieving document(s) responsive to the search query, and processing the textual fragment and the document(s) using entailment machine learning model(s) to generate prediction(s) of whether the at least one document corroborates or contradicts the textual fragment. When natural language (NL) responsive to the query is rendered at a client device, annotation(s) may be rendered to express the prediction(s).