NATURAL LANGUAGE TRAINING AND/OR AUGMENTATION WITH LARGE LANGUAGE MODELS
The techniques described herein enhance the operations of natural language generation systems through training and/or augmentation by a large language model. In a first example, the large language model can execute training operations by processing a training dataset to produce a natural language ou...
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Patent |
| Sprache: | eng |
| Schlagworte: | |
| 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 | WANG, Shuohang ITER, Dan ZENG, Nanshan XU, Yichong LIU, Yang ZHU, Chenguang SHARMA, Hiteshi |
| description | The techniques described herein enhance the operations of natural language generation systems through training and/or augmentation by a large language model. In a first example, the large language model can execute training operations by processing a training dataset to produce a natural language output. The natural language generation system can analyze the training dataset and the natural language output to generate a natural language output mimicking the output of the large language model. The large language model can then evaluate the output of the natural language generation system to iteratively adjust and improve the quality of natural language outputs. In a second example, the large language can augment a small language model in executing natural language tasks. This is accomplished by retrieving external information using the large language model to generate an augmentation input to provide context and a language framework to the small language model to enhance overall outputs. |
| format | Patent |
| fullrecord | <record><control><sourceid>epo_EVB</sourceid><recordid>TN_cdi_epo_espacenet_US2024346254A1</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>US2024346254A1</sourcerecordid><originalsourceid>FETCH-epo_espacenet_US2024346254A13</originalsourceid><addsrcrecordid>eNrjZPDwcwwJDXL0UfBx9HMPdXR3VQgJcvT08_RzV3D0c9H3D1JwDHX3dfULcQzx9PdTCPcM8QAqDQKqg2vw9Xdx9QnmYWBNS8wpTuWF0twMym6uIc4euqkF-fGpxQWJyal5qSXxocFGBkYmxiZmRqYmjobGxKkCALQ-Lbg</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>patent</recordtype></control><display><type>patent</type><title>NATURAL LANGUAGE TRAINING AND/OR AUGMENTATION WITH LARGE LANGUAGE MODELS</title><source>esp@cenet</source><creator>WANG, Shuohang ; ITER, Dan ; ZENG, Nanshan ; XU, Yichong ; LIU, Yang ; ZHU, Chenguang ; SHARMA, Hiteshi</creator><creatorcontrib>WANG, Shuohang ; ITER, Dan ; ZENG, Nanshan ; XU, Yichong ; LIU, Yang ; ZHU, Chenguang ; SHARMA, Hiteshi</creatorcontrib><description>The techniques described herein enhance the operations of natural language generation systems through training and/or augmentation by a large language model. In a first example, the large language model can execute training operations by processing a training dataset to produce a natural language output. The natural language generation system can analyze the training dataset and the natural language output to generate a natural language output mimicking the output of the large language model. The large language model can then evaluate the output of the natural language generation system to iteratively adjust and improve the quality of natural language outputs. In a second example, the large language can augment a small language model in executing natural language tasks. This is accomplished by retrieving external information using the large language model to generate an augmentation input to provide context and a language framework to the small language model to enhance overall outputs.</description><language>eng</language><subject>CALCULATING ; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS ; 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&date=20241017&DB=EPODOC&CC=US&NR=2024346254A1$$EHTML$$P50$$Gepo$$Hfree_for_read</linktohtml><link.rule.ids>230,308,776,881,25542,76289</link.rule.ids><linktorsrc>$$Uhttps://worldwide.espacenet.com/publicationDetails/biblio?FT=D&date=20241017&DB=EPODOC&CC=US&NR=2024346254A1$$EView_record_in_European_Patent_Office$$FView_record_in_$$GEuropean_Patent_Office$$Hfree_for_read</linktorsrc></links><search><creatorcontrib>WANG, Shuohang</creatorcontrib><creatorcontrib>ITER, Dan</creatorcontrib><creatorcontrib>ZENG, Nanshan</creatorcontrib><creatorcontrib>XU, Yichong</creatorcontrib><creatorcontrib>LIU, Yang</creatorcontrib><creatorcontrib>ZHU, Chenguang</creatorcontrib><creatorcontrib>SHARMA, Hiteshi</creatorcontrib><title>NATURAL LANGUAGE TRAINING AND/OR AUGMENTATION WITH LARGE LANGUAGE MODELS</title><description>The techniques described herein enhance the operations of natural language generation systems through training and/or augmentation by a large language model. In a first example, the large language model can execute training operations by processing a training dataset to produce a natural language output. The natural language generation system can analyze the training dataset and the natural language output to generate a natural language output mimicking the output of the large language model. The large language model can then evaluate the output of the natural language generation system to iteratively adjust and improve the quality of natural language outputs. In a second example, the large language can augment a small language model in executing natural language tasks. This is accomplished by retrieving external information using the large language model to generate an augmentation input to provide context and a language framework to the small language model to enhance overall outputs.</description><subject>CALCULATING</subject><subject>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</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>eNrjZPDwcwwJDXL0UfBx9HMPdXR3VQgJcvT08_RzV3D0c9H3D1JwDHX3dfULcQzx9PdTCPcM8QAqDQKqg2vw9Xdx9QnmYWBNS8wpTuWF0twMym6uIc4euqkF-fGpxQWJyal5qSXxocFGBkYmxiZmRqYmjobGxKkCALQ-Lbg</recordid><startdate>20241017</startdate><enddate>20241017</enddate><creator>WANG, Shuohang</creator><creator>ITER, Dan</creator><creator>ZENG, Nanshan</creator><creator>XU, Yichong</creator><creator>LIU, Yang</creator><creator>ZHU, Chenguang</creator><creator>SHARMA, Hiteshi</creator><scope>EVB</scope></search><sort><creationdate>20241017</creationdate><title>NATURAL LANGUAGE TRAINING AND/OR AUGMENTATION WITH LARGE LANGUAGE MODELS</title><author>WANG, Shuohang ; ITER, Dan ; ZENG, Nanshan ; XU, Yichong ; LIU, Yang ; ZHU, Chenguang ; SHARMA, Hiteshi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-epo_espacenet_US2024346254A13</frbrgroupid><rsrctype>patents</rsrctype><prefilter>patents</prefilter><language>eng</language><creationdate>2024</creationdate><topic>CALCULATING</topic><topic>COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS</topic><topic>COMPUTING</topic><topic>COUNTING</topic><topic>ELECTRIC DIGITAL DATA PROCESSING</topic><topic>PHYSICS</topic><toplevel>online_resources</toplevel><creatorcontrib>WANG, Shuohang</creatorcontrib><creatorcontrib>ITER, Dan</creatorcontrib><creatorcontrib>ZENG, Nanshan</creatorcontrib><creatorcontrib>XU, Yichong</creatorcontrib><creatorcontrib>LIU, Yang</creatorcontrib><creatorcontrib>ZHU, Chenguang</creatorcontrib><creatorcontrib>SHARMA, Hiteshi</creatorcontrib><collection>esp@cenet</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>WANG, Shuohang</au><au>ITER, Dan</au><au>ZENG, Nanshan</au><au>XU, Yichong</au><au>LIU, Yang</au><au>ZHU, Chenguang</au><au>SHARMA, Hiteshi</au><format>patent</format><genre>patent</genre><ristype>GEN</ristype><title>NATURAL LANGUAGE TRAINING AND/OR AUGMENTATION WITH LARGE LANGUAGE MODELS</title><date>2024-10-17</date><risdate>2024</risdate><abstract>The techniques described herein enhance the operations of natural language generation systems through training and/or augmentation by a large language model. In a first example, the large language model can execute training operations by processing a training dataset to produce a natural language output. The natural language generation system can analyze the training dataset and the natural language output to generate a natural language output mimicking the output of the large language model. The large language model can then evaluate the output of the natural language generation system to iteratively adjust and improve the quality of natural language outputs. In a second example, the large language can augment a small language model in executing natural language tasks. This is accomplished by retrieving external information using the large language model to generate an augmentation input to provide context and a language framework to the small language model to enhance overall outputs.</abstract><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | |
| ispartof | |
| issn | |
| language | eng |
| recordid | cdi_epo_espacenet_US2024346254A1 |
| source | esp@cenet |
| subjects | CALCULATING COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS COMPUTING COUNTING ELECTRIC DIGITAL DATA PROCESSING PHYSICS |
| title | NATURAL LANGUAGE TRAINING AND/OR AUGMENTATION WITH LARGE LANGUAGE MODELS |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-06T03%3A06%3A16IST&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=WANG,%20Shuohang&rft.date=2024-10-17&rft_id=info:doi/&rft_dat=%3Cepo_EVB%3EUS2024346254A1%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 |