Evaluating the Feasibility of Using Smaller Large Language Models for Generating Impressions from Findings in Radiology Reports

Deli-Slavova, Margarita; Hough, Julian

doi:10.1007/978-3-032-00652-3_24

Conference Paper/Proceeding/Abstract 244 views 75 downloads

Evaluating the Feasibility of Using Smaller Large Language Models for Generating Impressions from Findings in Radiology Reports

Margarita Deli-Slavova, Julian Hough

Lecture Notes in Computer Science, Volume: 16038, Pages: 339 - 350

Swansea University Authors: Margarita Deli-Slavova, Julian Hough

PDF | Accepted Manuscript

Author accepted manuscript document released under the terms of a Creative Commons CC-BY licence using the Swansea University Research Publications Policy (rights retention).
Download (269.75KB)

Check full text

DOI (Published version): 10.1007/978-3-032-00652-3_24

Published in:	Lecture Notes in Computer Science
ISBN:	9783032006516 9783032006523
ISSN:	0302-9743 1611-3349
Published:	Cham Springer Nature Switzerland 2026
Online Access:	Check full text
URI:	https://cronfa.swan.ac.uk/Record/cronfa69805

first_indexed	2025-06-24T10:44:47Z
last_indexed	2025-09-16T07:26:19Z
id	cronfa69805
recordtype	SURis
fullrecord	<?xml version="1.0"?><rfc1807><datestamp>2025-09-15T17:15:14.7486598</datestamp><bib-version>v2</bib-version><id>69805</id><entry>2025-06-24</entry><title>Evaluating the Feasibility of Using Smaller Large Language Models for Generating Impressions from Findings in Radiology Reports</title><swanseaauthors><author><sid>1218f2ae03a2a131ae5bdbf0ccc08b2b</sid><firstname>Margarita</firstname><surname>Deli-Slavova</surname><name>Margarita Deli-Slavova</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>082d773ae261d2bbf49434dd2608ab40</sid><ORCID>0000-0002-4345-6759</ORCID><firstname>Julian</firstname><surname>Hough</surname><name>Julian Hough</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2025-06-24</date><abstract/><type>Conference Paper/Proceeding/Abstract</type><journal>Lecture Notes in Computer Science</journal><volume>16038</volume><journalNumber/><paginationStart>339</paginationStart><paginationEnd>350</paginationEnd><publisher>Springer Nature Switzerland</publisher><placeOfPublication>Cham</placeOfPublication><isbnPrint>9783032006516</isbnPrint><isbnElectronic>9783032006523</isbnElectronic><issnPrint>0302-9743</issnPrint><issnElectronic>1611-3349</issnElectronic><keywords>NLP; Radiology; Summarisation; In-context learning</keywords><publishedDay>1</publishedDay><publishedMonth>1</publishedMonth><publishedYear>2026</publishedYear><publishedDate>2026-01-01</publishedDate><doi>10.1007/978-3-032-00652-3_24</doi><url/><notes/><college>COLLEGE NANME</college><CollegeCode>COLLEGE CODE</CollegeCode><institution>Swansea University</institution><apcterm>Not Required</apcterm><funders>This work was partly funded by the UKRI EPSRC CDT for Enhancing Human Interactions and Collaborations with Data and Intelligence Driven Systems, EP/S021892/1. Hough’s work is partly funded by the EPSRC FLUIDITY project, EP/X009343/1.</funders><projectreference/><lastEdited>2025-09-15T17:15:14.7486598</lastEdited><Created>2025-06-24T11:40:57.0325553</Created><path><level id="1">Faculty of Science and Engineering</level><level id="2">School of Mathematics and Computer Science - Computer Science</level></path><authors><author><firstname>Margarita</firstname><surname>Deli-Slavova</surname><order>1</order></author><author><firstname>Julian</firstname><surname>Hough</surname><orcid>0000-0002-4345-6759</orcid><order>2</order></author></authors><documents><document><filename>69805__34556__9ddd55cedbb04ce9b85009e5ee974642.pdf</filename><originalFilename>DelislavovaHough2025.pdf</originalFilename><uploaded>2025-06-24T11:43:17.0474403</uploaded><type>Output</type><contentLength>276228</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><embargoDate>2025-07-24T00:00:00.0000000</embargoDate><documentNotes>Author accepted manuscript document released under the terms of a Creative Commons CC-BY licence using the Swansea University Research Publications Policy (rights retention).</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/deed.en</licence></document></documents><OutputDurs/></rfc1807>
spelling	2025-09-15T17:15:14.7486598 v2 69805 2025-06-24 Evaluating the Feasibility of Using Smaller Large Language Models for Generating Impressions from Findings in Radiology Reports 1218f2ae03a2a131ae5bdbf0ccc08b2b Margarita Deli-Slavova Margarita Deli-Slavova true false 082d773ae261d2bbf49434dd2608ab40 0000-0002-4345-6759 Julian Hough Julian Hough true false 2025-06-24 Conference Paper/Proceeding/Abstract Lecture Notes in Computer Science 16038 339 350 Springer Nature Switzerland Cham 9783032006516 9783032006523 0302-9743 1611-3349 NLP; Radiology; Summarisation; In-context learning 1 1 2026 2026-01-01 10.1007/978-3-032-00652-3_24 COLLEGE NANME COLLEGE CODE Swansea University Not Required This work was partly funded by the UKRI EPSRC CDT for Enhancing Human Interactions and Collaborations with Data and Intelligence Driven Systems, EP/S021892/1. Hough’s work is partly funded by the EPSRC FLUIDITY project, EP/X009343/1. 2025-09-15T17:15:14.7486598 2025-06-24T11:40:57.0325553 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Margarita Deli-Slavova 1 Julian Hough 0000-0002-4345-6759 2 69805__34556__9ddd55cedbb04ce9b85009e5ee974642.pdf DelislavovaHough2025.pdf 2025-06-24T11:43:17.0474403 Output 276228 application/pdf Accepted Manuscript true 2025-07-24T00:00:00.0000000 Author accepted manuscript document released under the terms of a Creative Commons CC-BY licence using the Swansea University Research Publications Policy (rights retention). true eng https://creativecommons.org/licenses/by/4.0/deed.en
title	Evaluating the Feasibility of Using Smaller Large Language Models for Generating Impressions from Findings in Radiology Reports
spellingShingle	Evaluating the Feasibility of Using Smaller Large Language Models for Generating Impressions from Findings in Radiology Reports Margarita Deli-Slavova Julian Hough
title_short	Evaluating the Feasibility of Using Smaller Large Language Models for Generating Impressions from Findings in Radiology Reports
title_full	Evaluating the Feasibility of Using Smaller Large Language Models for Generating Impressions from Findings in Radiology Reports
title_fullStr	Evaluating the Feasibility of Using Smaller Large Language Models for Generating Impressions from Findings in Radiology Reports
title_full_unstemmed	Evaluating the Feasibility of Using Smaller Large Language Models for Generating Impressions from Findings in Radiology Reports
title_sort	Evaluating the Feasibility of Using Smaller Large Language Models for Generating Impressions from Findings in Radiology Reports
author_id_str_mv	1218f2ae03a2a131ae5bdbf0ccc08b2b 082d773ae261d2bbf49434dd2608ab40
author_id_fullname_str_mv	1218f2ae03a2a131ae5bdbf0ccc08b2b_*_Margarita Deli-Slavova 082d773ae261d2bbf49434dd2608ab40_*_Julian Hough
author	Margarita Deli-Slavova Julian Hough
author2	Margarita Deli-Slavova Julian Hough
format	Conference Paper/Proceeding/Abstract
container_title	Lecture Notes in Computer Science
container_volume	16038
container_start_page	339
publishDate	2026
institution	Swansea University
isbn	9783032006516 9783032006523
issn	0302-9743 1611-3349
doi_str_mv	10.1007/978-3-032-00652-3_24
publisher	Springer Nature Switzerland
college_str	Faculty of Science and Engineering
hierarchytype
hierarchy_top_id	facultyofscienceandengineering
hierarchy_top_title	Faculty of Science and Engineering
hierarchy_parent_id	facultyofscienceandengineering
hierarchy_parent_title	Faculty of Science and Engineering
department_str	School of Mathematics and Computer Science - Computer Science{{{_:::_}}}Faculty of Science and Engineering{{{_:::_}}}School of Mathematics and Computer Science - Computer Science
document_store_str	1
active_str	0
published_date	2026-01-01T07:43:53Z
_version_	1850744015734964224
score	11.08895

Evaluating the Feasibility of Using Smaller Large Language Models for Generating Impressions from Findings in Radiology Reports

Similar Items