No Cover Image

Journal article 32 views

Identifying How UK Legislation Is Applied in Case Law: An Ensemble LLM Approach Using LegalDocML

Safia Kanwal, Livio Robaldo Orcid Logo, Stergios Aidinlis, JOSEPH ANIM, Davide Liga

Journal of Computational Law and Legal Technology, Pages: 1 - 18

Swansea University Authors: Livio Robaldo Orcid Logo, JOSEPH ANIM

  • 71990.VOR.pdf

    PDF | Version of Record

    © The Author(s) 2026. This is an open access article under the CC BY License .

    Download (771.53KB)

DOI (Published version): 10.47852/bonviewjcllt62029448

Abstract

Legal judgments derive their value not only from stating what the law is but also from showing how legal principles are applied to the facts of specific disputes. This applicative step, central to doctrines such as stare decisis, remains underexplored in legal artificial intelligence (AI) research,...

Full description

Published in: Journal of Computational Law and Legal Technology
Published: Bon View Publishing Pte Ltd. 2026
URI: https://cronfa.swan.ac.uk/Record/cronfa71990
first_indexed 2026-05-29T09:26:09Z
last_indexed 2026-05-30T16:21:00Z
id cronfa71990
recordtype SURis
fullrecord <?xml version="1.0" encoding="utf-8"?><rfc1807 xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns:xsd="http://www.w3.org/2001/XMLSchema"><bib-version>v2</bib-version><id>71990</id><entry>2026-05-29</entry><title>Identifying How UK Legislation Is Applied in Case Law: An Ensemble LLM Approach Using LegalDocML</title><swanseaauthors><author><sid>b711cf9f3a7821ec52bd1e53b4f6cf9e</sid><ORCID>0000-0003-4713-8990</ORCID><firstname>Livio</firstname><surname>Robaldo</surname><name>Livio Robaldo</name><active>true</active><ethesisStudent>false</ethesisStudent></author><author><sid>58e2beb6a882b1d451723fcbf84cfb9c</sid><firstname>JOSEPH</firstname><surname>ANIM</surname><name>JOSEPH ANIM</name><active>true</active><ethesisStudent>false</ethesisStudent></author></swanseaauthors><date>2026-05-29</date><deptcode>HRCL</deptcode><abstract>Legal judgments derive their value not only from stating what the law is but also from showing how legal principles are applied to the facts of specific disputes. This applicative step, central to doctrines such as stare decisis, remains underexplored in legal artificial intelligence (AI) research, which has largely focused on tasks such as retrieval and classification. Yet effective AI support for legal practice requires transparent methods that trace how statutes are applied in case law. This paper introduces a methodology for bridging UK statutory law with its judicial application by combining large language models (LLMs) with structured LegalDocML data. We process official LegalDocML files published by The National Archives, meticulously curated and validated by legal experts as part of a nationwide modernization of legislative publishing. The UK is among the few countries to provide all legislation and case law in LegalDocML, and to our knowledge, this study is the first substantial academic use of this resource with LLMs for the analysis of how legislation is applied in case law. Our results show that integrating bottom-up neural inference with top-down expert-curated XML data allows the proposed framework to identify phrase-level applications of legislation in case law with high accuracy and explainability. This approach advances practitioner-oriented legal AI and lays the foundation for next-generation LegalTech tools that support precedent analysis and traceable legal reasoning.</abstract><type>Journal Article</type><journal>Journal of Computational Law and Legal Technology</journal><volume>0</volume><journalNumber/><paginationStart>1</paginationStart><paginationEnd>18</paginationEnd><publisher>Bon View Publishing Pte Ltd.</publisher><placeOfPublication/><isbnPrint/><isbnElectronic/><issnPrint/><issnElectronic/><keywords>judicial application of statutes, phrase-level linking of legislation and case law, large language models, LegalDocML</keywords><publishedDay>29</publishedDay><publishedMonth>5</publishedMonth><publishedYear>2026</publishedYear><publishedDate>2026-05-29</publishedDate><doi>10.47852/bonviewjcllt62029448</doi><url/><notes/><college>COLLEGE NANME</college><department>Hillary Rodham Clinton Law School</department><CollegeCode>COLLEGE CODE</CollegeCode><DepartmentCode>HRCL</DepartmentCode><institution>Swansea University</institution><apcterm>Not Required</apcterm><funders>This paper was supported by Innovate UK project “Odyssey—Opening the National Archives Legal Data to AI forAccess to Justice (A2J),” Innovate UK 10106412.</funders><projectreference>10106412</projectreference><lastEdited>2026-06-02T15:49:34.4525457</lastEdited><Created>2026-05-29T10:22:16.1994139</Created><path><level id="1">Faculty of Humanities and Social Sciences</level><level id="2">Hilary Rodham Clinton School of Law</level></path><authors><author><firstname>Safia</firstname><surname>Kanwal</surname><order>1</order></author><author><firstname>Livio</firstname><surname>Robaldo</surname><orcid>0000-0003-4713-8990</orcid><order>2</order></author><author><firstname>Stergios</firstname><surname>Aidinlis</surname><order>3</order></author><author><firstname>JOSEPH</firstname><surname>ANIM</surname><order>4</order></author><author><firstname>Davide</firstname><surname>Liga</surname><order>5</order></author></authors><documents><document><filename>71990__36846__f504f30b127d4f29ae2d3cd0f24abc5b.pdf</filename><originalFilename>71990.VOR.pdf</originalFilename><uploaded>2026-06-02T15:41:12.2793240</uploaded><type>Output</type><contentLength>790051</contentLength><contentType>application/pdf</contentType><version>Version of Record</version><cronfaStatus>true</cronfaStatus><documentNotes>© The Author(s) 2026. This is an open access article under the CC BY License .</documentNotes><copyrightCorrect>true</copyrightCorrect><language>eng</language><licence>https://creativecommons.org/licenses/by/4.0/</licence></document></documents><OutputDurs/></rfc1807>
spelling v2 71990 2026-05-29 Identifying How UK Legislation Is Applied in Case Law: An Ensemble LLM Approach Using LegalDocML b711cf9f3a7821ec52bd1e53b4f6cf9e 0000-0003-4713-8990 Livio Robaldo Livio Robaldo true false 58e2beb6a882b1d451723fcbf84cfb9c JOSEPH ANIM JOSEPH ANIM true false 2026-05-29 HRCL Legal judgments derive their value not only from stating what the law is but also from showing how legal principles are applied to the facts of specific disputes. This applicative step, central to doctrines such as stare decisis, remains underexplored in legal artificial intelligence (AI) research, which has largely focused on tasks such as retrieval and classification. Yet effective AI support for legal practice requires transparent methods that trace how statutes are applied in case law. This paper introduces a methodology for bridging UK statutory law with its judicial application by combining large language models (LLMs) with structured LegalDocML data. We process official LegalDocML files published by The National Archives, meticulously curated and validated by legal experts as part of a nationwide modernization of legislative publishing. The UK is among the few countries to provide all legislation and case law in LegalDocML, and to our knowledge, this study is the first substantial academic use of this resource with LLMs for the analysis of how legislation is applied in case law. Our results show that integrating bottom-up neural inference with top-down expert-curated XML data allows the proposed framework to identify phrase-level applications of legislation in case law with high accuracy and explainability. This approach advances practitioner-oriented legal AI and lays the foundation for next-generation LegalTech tools that support precedent analysis and traceable legal reasoning. Journal Article Journal of Computational Law and Legal Technology 0 1 18 Bon View Publishing Pte Ltd. judicial application of statutes, phrase-level linking of legislation and case law, large language models, LegalDocML 29 5 2026 2026-05-29 10.47852/bonviewjcllt62029448 COLLEGE NANME Hillary Rodham Clinton Law School COLLEGE CODE HRCL Swansea University Not Required This paper was supported by Innovate UK project “Odyssey—Opening the National Archives Legal Data to AI forAccess to Justice (A2J),” Innovate UK 10106412. 10106412 2026-06-02T15:49:34.4525457 2026-05-29T10:22:16.1994139 Faculty of Humanities and Social Sciences Hilary Rodham Clinton School of Law Safia Kanwal 1 Livio Robaldo 0000-0003-4713-8990 2 Stergios Aidinlis 3 JOSEPH ANIM 4 Davide Liga 5 71990__36846__f504f30b127d4f29ae2d3cd0f24abc5b.pdf 71990.VOR.pdf 2026-06-02T15:41:12.2793240 Output 790051 application/pdf Version of Record true © The Author(s) 2026. This is an open access article under the CC BY License . true eng https://creativecommons.org/licenses/by/4.0/
title Identifying How UK Legislation Is Applied in Case Law: An Ensemble LLM Approach Using LegalDocML
spellingShingle Identifying How UK Legislation Is Applied in Case Law: An Ensemble LLM Approach Using LegalDocML
Livio Robaldo
JOSEPH ANIM
title_short Identifying How UK Legislation Is Applied in Case Law: An Ensemble LLM Approach Using LegalDocML
title_full Identifying How UK Legislation Is Applied in Case Law: An Ensemble LLM Approach Using LegalDocML
title_fullStr Identifying How UK Legislation Is Applied in Case Law: An Ensemble LLM Approach Using LegalDocML
title_full_unstemmed Identifying How UK Legislation Is Applied in Case Law: An Ensemble LLM Approach Using LegalDocML
title_sort Identifying How UK Legislation Is Applied in Case Law: An Ensemble LLM Approach Using LegalDocML
author_id_str_mv b711cf9f3a7821ec52bd1e53b4f6cf9e
58e2beb6a882b1d451723fcbf84cfb9c
author_id_fullname_str_mv b711cf9f3a7821ec52bd1e53b4f6cf9e_***_Livio Robaldo
58e2beb6a882b1d451723fcbf84cfb9c_***_JOSEPH ANIM
author Livio Robaldo
JOSEPH ANIM
author2 Safia Kanwal
Livio Robaldo
Stergios Aidinlis
JOSEPH ANIM
Davide Liga
format Journal article
container_title Journal of Computational Law and Legal Technology
container_volume 0
container_start_page 1
publishDate 2026
institution Swansea University
doi_str_mv 10.47852/bonviewjcllt62029448
publisher Bon View Publishing Pte Ltd.
college_str Faculty of Humanities and Social Sciences
hierarchytype
hierarchy_top_id facultyofhumanitiesandsocialsciences
hierarchy_top_title Faculty of Humanities and Social Sciences
hierarchy_parent_id facultyofhumanitiesandsocialsciences
hierarchy_parent_title Faculty of Humanities and Social Sciences
department_str Hilary Rodham Clinton School of Law{{{_:::_}}}Faculty of Humanities and Social Sciences{{{_:::_}}}Hilary Rodham Clinton School of Law
document_store_str 1
active_str 0
description Legal judgments derive their value not only from stating what the law is but also from showing how legal principles are applied to the facts of specific disputes. This applicative step, central to doctrines such as stare decisis, remains underexplored in legal artificial intelligence (AI) research, which has largely focused on tasks such as retrieval and classification. Yet effective AI support for legal practice requires transparent methods that trace how statutes are applied in case law. This paper introduces a methodology for bridging UK statutory law with its judicial application by combining large language models (LLMs) with structured LegalDocML data. We process official LegalDocML files published by The National Archives, meticulously curated and validated by legal experts as part of a nationwide modernization of legislative publishing. The UK is among the few countries to provide all legislation and case law in LegalDocML, and to our knowledge, this study is the first substantial academic use of this resource with LLMs for the analysis of how legislation is applied in case law. Our results show that integrating bottom-up neural inference with top-down expert-curated XML data allows the proposed framework to identify phrase-level applications of legislation in case law with high accuracy and explainability. This approach advances practitioner-oriented legal AI and lays the foundation for next-generation LegalTech tools that support precedent analysis and traceable legal reasoning.
published_date 2026-05-29T15:49:36Z
_version_ 1866897058996158464
score 10.701432

Similar Items