ATTRIBUTION VERIFICATION FOR ANSWERS AND SUMMARIES GENERATED FROM LARGE LANGUAGE MODELS (LLMS)

ATTRIBUTION VERIFICATION FOR ANSWERS AND SUMMARIES GENERATED FROM LARGE LANGUAGE MODELS (LLMS)

Systems and methods for verifying attribution of quotations, generated by a large language model (LLM), to a source document are disclosed herein. Upon a request to summarize a source document or process a question that is answerable from a document, an LLM prompt is formed with the request or quest...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: JIANG, Jingtian, RUSSELL, James Simon, PASCH, Mary Sugino David
Format: Patent
Sprache:eng
Schlagworte:
CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page
container_issue
container_start_page
container_title
container_volume
creator JIANG, Jingtian
RUSSELL, James Simon
PASCH, Mary Sugino David
description Systems and methods for verifying attribution of quotations, generated by a large language model (LLM), to a source document are disclosed herein. Upon a request to summarize a source document or process a question that is answerable from a document, an LLM prompt is formed with the request or question along with the content of the source document. The LLM prompt is configured to cause an LLM to generate quotes that are intended to be from the source document. The output of the LLM, including the quotes, is then verified against the source document.
format Patent
fullrecord <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2024296295A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2024296295A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2024296295A13</originalsourceid><addsrcrecordid>eNqNissKwjAQRbtxIeo_DLjRhaDxAV2OzaQG8oBJojtLkbgSLdT_xyJ-gJtzzoU7Lq4YI-tjito7OBNrpSv8DuUZ0IULcRgsISRrkTUFqMkRYyQJir0Fg1zTQFcnHMJ6SSbAwhgbltNidG8ffZ79PCnmimJ1WuXu1eS-a2_5md9NCmItdqI8iHKPm-1_rw_6tzPV</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>ATTRIBUTION VERIFICATION FOR ANSWERS AND SUMMARIES GENERATED FROM LARGE LANGUAGE MODELS (LLMS)</title><source>esp@cenet</source><creator>JIANG, Jingtian ; RUSSELL, James Simon ; PASCH, Mary Sugino David</creator><creatorcontrib>JIANG, Jingtian ; RUSSELL, James Simon ; PASCH, Mary Sugino David</creatorcontrib><description>Systems and methods for verifying attribution of quotations, generated by a large language model (LLM), to a source document are disclosed herein. Upon a request to summarize a source document or process a question that is answerable from a document, an LLM prompt is formed with the request or question along with the content of the source document. The LLM prompt is configured to cause an LLM to generate quotes that are intended to be from the source document. The output of the LLM, including the quotes, is then verified against the source document.</description><language>eng</language><subject>CALCULATING ; COMPUTING ; COUNTING ; ELECTRIC DIGITAL DATA PROCESSING ; PHYSICS</subject><creationdate>2024</creationdate><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20240905&amp;DB=EPODOC&amp;CC=US&amp;NR=2024296295A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,309,782,887,25571,76555</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&amp;date=20240905&amp;DB=EPODOC&amp;CC=US&amp;NR=2024296295A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>JIANG, Jingtian</creatorcontrib><creatorcontrib>RUSSELL, James Simon</creatorcontrib><creatorcontrib>PASCH, Mary Sugino David</creatorcontrib><title>ATTRIBUTION VERIFICATION FOR ANSWERS AND SUMMARIES GENERATED FROM LARGE LANGUAGE MODELS (LLMS)</title><description>Systems and methods for verifying attribution of quotations, generated by a large language model (LLM), to a source document are disclosed herein. Upon a request to summarize a source document or process a question that is answerable from a document, an LLM prompt is formed with the request or question along with the content of the source document. The LLM prompt is configured to cause an LLM to generate quotes that are intended to be from the source document. The output of the LLM, including the quotes, is then verified against the source document.</description><subject>CALCULATING</subject><subject>COMPUTING</subject><subject>COUNTING</subject><subject>ELECTRIC DIGITAL DATA PROCESSING</subject><subject>PHYSICS</subject><fulltext>true</fulltext><rsrctype>patent</rsrctype><creationdate>2024</creationdate><recordtype>patent</recordtype><sourceid>EVB</sourceid><recordid>eNqNissKwjAQRbtxIeo_DLjRhaDxAV2OzaQG8oBJojtLkbgSLdT_xyJ-gJtzzoU7Lq4YI-tjito7OBNrpSv8DuUZ0IULcRgsISRrkTUFqMkRYyQJir0Fg1zTQFcnHMJ6SSbAwhgbltNidG8ffZ79PCnmimJ1WuXu1eS-a2_5md9NCmItdqI8iHKPm-1_rw_6tzPV</recordid><startdate>20240905</startdate><enddate>20240905</enddate><creator>JIANG, Jingtian</creator><creator>RUSSELL, James Simon</creator><creator>PASCH, Mary Sugino David</creator><scope>EVB</scope></search><sort><creationdate>20240905</creationdate><title>ATTRIBUTION VERIFICATION FOR ANSWERS AND SUMMARIES GENERATED FROM LARGE LANGUAGE MODELS (LLMS)</title><author>JIANG, Jingtian ; RUSSELL, James Simon ; PASCH, Mary Sugino David</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2024296295A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>JIANG, Jingtian</creatorcontrib><creatorcontrib>RUSSELL, James Simon</creatorcontrib><creatorcontrib>PASCH, Mary Sugino David</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>JIANG, Jingtian</au><au>RUSSELL, James Simon</au><au>PASCH, Mary Sugino David</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>ATTRIBUTION VERIFICATION FOR ANSWERS AND SUMMARIES GENERATED FROM LARGE LANGUAGE MODELS (LLMS)</title><date>2024-09-05</date><risdate>2024</risdate><abstract>Systems and methods for verifying attribution of quotations, generated by a large language model (LLM), to a source document are disclosed herein. Upon a request to summarize a source document or process a question that is answerable from a document, an LLM prompt is formed with the request or question along with the content of the source document. The LLM prompt is configured to cause an LLM to generate quotes that are intended to be from the source document. The output of the LLM, including the quotes, is then verified against the source document.</abstract><oa>free_for_read</oa></addata></record>
fulltext fulltext_linktorsrc
identifier
ispartof
issn
language eng
recordid cdi_epo_espacenet_US2024296295A1
source esp@cenet
subjects CALCULATING
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
PHYSICS
title ATTRIBUTION VERIFICATION FOR ANSWERS AND SUMMARIES GENERATED FROM LARGE LANGUAGE MODELS (LLMS)
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-05T04%3A08%3A47IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-epo_EVB&rft_val_fmt=info:ofi/fmt:kev:mtx:patent&rft.genre=patent&rft.au=JIANG,%20Jingtian&rft.date=2024-09-05&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2024296295A1%3C/epo_EVB%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rfr_iscdi=true