No Cover Image

Conference Paper/Proceeding/Abstract 29 views

An Exploration-Analysis-Disambiguation Reasoning Framework for Word Sense Disambiguation with Low-Parameter LLMs

Deshan Sumanathilaka Orcid Logo, Nicholas Micallef Orcid Logo, Julian Hough Orcid Logo

The Fifteenth biennial Language Resources and Evaluation Conference (LREC)

Swansea University Authors: Deshan Sumanathilaka Orcid Logo, Nicholas Micallef Orcid Logo, Julian Hough Orcid Logo

Abstract

Word Sense Disambiguation (WSD) remains a key challenge in Natural Language Processing (NLP), especially when dealing with rare or domain-specific senses that are often misinterpreted. While modern high-parameter Large Language Models (LLMs) such as GPT-4-Turbo have shown state-of-the-art WSD perfor...

Full description

Published in: The Fifteenth biennial Language Resources and Evaluation Conference (LREC)
Published:
URI: https://cronfa.swan.ac.uk/Record/cronfa71528
first_indexed 2026-03-03T14:55:09Z
last_indexed 2026-03-04T05:32:56Z
id cronfa71528
recordtype SURis
fullrecord <?xml version="1.0"?><rfc1807><datestamp>2026-03-03T14:55:07.9258605</datestamp><bib-version>v2</bib-version><id>71528</id><entry>2026-03-03</entry><title>An Exploration-Analysis-Disambiguation Reasoning Framework for Word Sense Disambiguation with Low-Parameter LLMs</title><swanseaauthors><author><sid>2fe44f0c1e7d845dc21bb6b00d5b2085</sid><ORCID>0009-0005-8933-6559</ORCID><firstname>Deshan</firstname><surname>Sumanathilaka</surname><name>Deshan Sumanathilaka</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>1cc4c84582d665b7ee08fb16f5454671</sid><ORCID>0000-0002-2683-8042</ORCID><firstname>Nicholas</firstname><surname>Micallef</surname><name>Nicholas Micallef</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>2026-03-03</date><deptcode>MACS</deptcode><abstract>Word Sense Disambiguation (WSD) remains a key challenge in Natural Language Processing (NLP), especially when dealing with rare or domain-specific senses that are often misinterpreted. While modern high-parameter Large Language Models (LLMs) such as GPT-4-Turbo have shown state-of-the-art WSD performance, their computational and energy demands limit scalability. This study investigates whether low-parameter LLMs (4B parameters) can achieve comparable results through fine-tuning strategies that emphasize reasoning-driven sense identification. Using the FEWS dataset augmented with semi-automated, rationale-rich annotations, we fine-tune eight small-scale open-source LLMs (e.g. Gemma and Qwen). Our results reveal that CoT-based reasoning combined with neighbour-word analysis achieves performance comparable to GPT-4-Turbo in zero-shot settings. Importantly, Gemma-3-4B and Qwen-3-4B models consistently outperform all medium-parameter baselines and state-of-the-art models on FEWS, with robust generalization to unseen senses. Furthermore, evaluation on the unseen ''Fool Me If You Can'' dataset confirms strong cross-domain adaptability without task-specific fine-tuning. This work demonstrates that with carefully crafted reasoning-centric fine-tuning, low-parameter LLMs can deliver accurate WSD while substantially reducing computational and energy demands.</abstract><type>Conference Paper/Proceeding/Abstract</type><journal>The Fifteenth biennial Language Resources and Evaluation Conference (LREC)</journal><volume/><journalNumber/><paginationStart/><paginationEnd/><publisher/><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic/><keywords>Word Sense Disambiguation, Low-parameter LLMs, Reasoning-driven Fine-tuning</keywords><publishedDay>0</publishedDay><publishedMonth>0</publishedMonth><publishedYear>0</publishedYear><publishedDate>0001-01-01</publishedDate><doi/><url/><notes/><college>COLLEGE NANME</college><department>Mathematics and Computer Science School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>MACS</DepartmentCode><institution>Swansea University</institution><apcterm/><funders/><projectreference/><lastEdited>2026-03-03T14:55:07.9258605</lastEdited><Created>2026-03-03T14:47:58.7796742</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>Deshan</firstname><surname>Sumanathilaka</surname><orcid>0009-0005-8933-6559</orcid><order>1</order></author><author><firstname>Nicholas</firstname><surname>Micallef</surname><orcid>0000-0002-2683-8042</orcid><order>2</order></author><author><firstname>Julian</firstname><surname>Hough</surname><orcid>0000-0002-4345-6759</orcid><order>3</order></author></authors><documents><document><filename>71528__36342__5b91a0e87b1c48c0b6133bbebc60c14c.pdf</filename><originalFilename>LREC.pdf</originalFilename><uploaded>2026-03-03T14:53:17.9812253</uploaded><type>Output</type><contentLength>273171</contentLength><contentType>application/pdf</contentType><version>Accepted Manuscript</version><cronfaStatus>true</cronfaStatus><copyrightCorrect>false</copyrightCorrect><language>English</language></document></documents><OutputDurs/></rfc1807>
spelling 2026-03-03T14:55:07.9258605 v2 71528 2026-03-03 An Exploration-Analysis-Disambiguation Reasoning Framework for Word Sense Disambiguation with Low-Parameter LLMs 2fe44f0c1e7d845dc21bb6b00d5b2085 0009-0005-8933-6559 Deshan Sumanathilaka Deshan Sumanathilaka true false 1cc4c84582d665b7ee08fb16f5454671 0000-0002-2683-8042 Nicholas Micallef Nicholas Micallef true false 082d773ae261d2bbf49434dd2608ab40 0000-0002-4345-6759 Julian Hough Julian Hough true false 2026-03-03 MACS Word Sense Disambiguation (WSD) remains a key challenge in Natural Language Processing (NLP), especially when dealing with rare or domain-specific senses that are often misinterpreted. While modern high-parameter Large Language Models (LLMs) such as GPT-4-Turbo have shown state-of-the-art WSD performance, their computational and energy demands limit scalability. This study investigates whether low-parameter LLMs (4B parameters) can achieve comparable results through fine-tuning strategies that emphasize reasoning-driven sense identification. Using the FEWS dataset augmented with semi-automated, rationale-rich annotations, we fine-tune eight small-scale open-source LLMs (e.g. Gemma and Qwen). Our results reveal that CoT-based reasoning combined with neighbour-word analysis achieves performance comparable to GPT-4-Turbo in zero-shot settings. Importantly, Gemma-3-4B and Qwen-3-4B models consistently outperform all medium-parameter baselines and state-of-the-art models on FEWS, with robust generalization to unseen senses. Furthermore, evaluation on the unseen ''Fool Me If You Can'' dataset confirms strong cross-domain adaptability without task-specific fine-tuning. This work demonstrates that with carefully crafted reasoning-centric fine-tuning, low-parameter LLMs can deliver accurate WSD while substantially reducing computational and energy demands. Conference Paper/Proceeding/Abstract The Fifteenth biennial Language Resources and Evaluation Conference (LREC) Word Sense Disambiguation, Low-parameter LLMs, Reasoning-driven Fine-tuning 0 0 0 0001-01-01 COLLEGE NANME Mathematics and Computer Science School COLLEGE CODE MACS Swansea University 2026-03-03T14:55:07.9258605 2026-03-03T14:47:58.7796742 Faculty of Science and Engineering School of Mathematics and Computer Science - Computer Science Deshan Sumanathilaka 0009-0005-8933-6559 1 Nicholas Micallef 0000-0002-2683-8042 2 Julian Hough 0000-0002-4345-6759 3 71528__36342__5b91a0e87b1c48c0b6133bbebc60c14c.pdf LREC.pdf 2026-03-03T14:53:17.9812253 Output 273171 application/pdf Accepted Manuscript true false English
title An Exploration-Analysis-Disambiguation Reasoning Framework for Word Sense Disambiguation with Low-Parameter LLMs
spellingShingle An Exploration-Analysis-Disambiguation Reasoning Framework for Word Sense Disambiguation with Low-Parameter LLMs
Deshan Sumanathilaka
Nicholas Micallef
Julian Hough
title_short An Exploration-Analysis-Disambiguation Reasoning Framework for Word Sense Disambiguation with Low-Parameter LLMs
title_full An Exploration-Analysis-Disambiguation Reasoning Framework for Word Sense Disambiguation with Low-Parameter LLMs
title_fullStr An Exploration-Analysis-Disambiguation Reasoning Framework for Word Sense Disambiguation with Low-Parameter LLMs
title_full_unstemmed An Exploration-Analysis-Disambiguation Reasoning Framework for Word Sense Disambiguation with Low-Parameter LLMs
title_sort An Exploration-Analysis-Disambiguation Reasoning Framework for Word Sense Disambiguation with Low-Parameter LLMs
author_id_str_mv 2fe44f0c1e7d845dc21bb6b00d5b2085
1cc4c84582d665b7ee08fb16f5454671
082d773ae261d2bbf49434dd2608ab40
author_id_fullname_str_mv 2fe44f0c1e7d845dc21bb6b00d5b2085_***_Deshan Sumanathilaka
1cc4c84582d665b7ee08fb16f5454671_***_Nicholas Micallef
082d773ae261d2bbf49434dd2608ab40_***_Julian Hough
author Deshan Sumanathilaka
Nicholas Micallef
Julian Hough
author2 Deshan Sumanathilaka
Nicholas Micallef
Julian Hough
format Conference Paper/Proceeding/Abstract
container_title The Fifteenth biennial Language Resources and Evaluation Conference (LREC)
institution Swansea University
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
description Word Sense Disambiguation (WSD) remains a key challenge in Natural Language Processing (NLP), especially when dealing with rare or domain-specific senses that are often misinterpreted. While modern high-parameter Large Language Models (LLMs) such as GPT-4-Turbo have shown state-of-the-art WSD performance, their computational and energy demands limit scalability. This study investigates whether low-parameter LLMs (4B parameters) can achieve comparable results through fine-tuning strategies that emphasize reasoning-driven sense identification. Using the FEWS dataset augmented with semi-automated, rationale-rich annotations, we fine-tune eight small-scale open-source LLMs (e.g. Gemma and Qwen). Our results reveal that CoT-based reasoning combined with neighbour-word analysis achieves performance comparable to GPT-4-Turbo in zero-shot settings. Importantly, Gemma-3-4B and Qwen-3-4B models consistently outperform all medium-parameter baselines and state-of-the-art models on FEWS, with robust generalization to unseen senses. Furthermore, evaluation on the unseen ''Fool Me If You Can'' dataset confirms strong cross-domain adaptability without task-specific fine-tuning. This work demonstrates that with carefully crafted reasoning-centric fine-tuning, low-parameter LLMs can deliver accurate WSD while substantially reducing computational and energy demands.
published_date 0001-01-01T05:32:56Z
_version_ 1858708309289205760
score 11.453587

Similar Items