Generating output sequences with inline evidence using language model neural networks
The system addresses the issues of unfounded claims and resource-intensive large language models by generating responses with evidence from contextual documents, optimizing computing load and ensuring accuracy and up-to-date information.
JP7842236B2Active Publication Date: 2026-04-07ジーディーエム·ホールディング·エルエルシー
Patent Information
- Authority / Receiving Office
- JP · JP
- Patent Type
- Patents
- Current Assignee / Owner
- Filing Date
- 2023-03-16
- Publication Date
- 2026-04-07
Smart Images

Figure 0007842236000002 
Figure 0007842236000003 
Figure 0007842236000004
Abstract
A method, system, and apparatus for generating an output sequence using a language model neural network, the method including a computer program encoded on a computer storage medium, wherein, in particular, the output sequence includes a response to an input query and in-line evidence including citations from context documents that support the response.
Need to check novelty before this filing date? Find Prior Art
Citation Information
Patent Citations
Determining rationale of cognitive system output
US20200134414A1
Utilizing external knowledge and memory networks in a question-answering system
US20200167428A1
Multiple instance machine learning for question answering systems
US9720981B1