Meticulously Unsupervised Entity Alignment with Large Language Models

Meticulously Unsupervised Entity Alignment with Large Language Models | Authorea try { document.documentElement.classList.add('js'); } catch (e) { } var _gaq = _gaq || []; _gaq.push(['_setAccount', 'G-8VDV14Y67G']); _gaq.push(['_trackPageview']); (function() { var ga = document.createElement('script'); ga.type = 'text/javascript'; ga.async = true; ga.src = ('https:' == document.location.protocol ? 'https://ssl' : 'http://www') + '.google-analytics.com/ga.js'; var s = document.getElementsByTagName('script')[0]; s.parentNode.insertBefore(ga, s); })(); Skip to main content Preprints Collections Wiley Open Research IET Open Research Ecological Society of Japan All Collections About About Authorea FAQs Contact Us Quick Search anywhere Search for preprint articles, keywords, etc. Search Search ADVANCED SEARCH SCROLL This is a preprint and has not been peer reviewed. Data may be preliminary. 30 September 2025 V1 Latest version Share on Meticulously Unsupervised Entity Alignment with Large Language Models Authors : Zhihuan Yan [email protected] , Yi Wang , Chongchong Zhang , Hengyang Wu , Liping Li , and Rong Peng Authors Info & Affiliations https://doi.org/10.22541/au.175921643.34240038/v1 160 views 109 downloads Contents Abstract Supplementary Material Information & Authors Metrics & Citations View Options References Figures Tables Media Share Abstract Knowledge graph entity alignment refers to the process of identifying and linking entities that refer to the same real-world object from different knowledge graphs. However, structural heterogeneity between knowledge graphs and scarcity of training data have always been two major challenges that impede entity alignment tasks. The advent of Large Language Models presents new avenues for entity knowledge completion and unsupervised EA, inspired by their extensive background knowledge and comprehensive capability to process semantic information. However, it is nontrivial to directly apply Large Language Models in addressing the aforementioned two challenges due to the following reasons: 1) it will blindly enrich entity knowledge in the absence of appropriate constraints; 2) it could generate noisy labels that may mislead the alignment. To this end, this paper presents a novel entity alignment framework, named LLM-Align , to effectively leverage Large Language Models for unsupervised entity alignment. Firstly, C onstrained Entity I nformation E nrichment ( CIE ) technique is devised, which employs attributes and relationships existing in the KGs to constrain the generation process of LLMs, which further alleviates structural heterogeneity between aligned entities. Subsequently, a C ode-formatted P rompt T emplate ( CPT ) was designed to assist the Large Language Models in labelling aligned entity pairs from candidate pairs generating via both semantic and structural similarities. Ultimately, C ombinatorial O ptimization method based entity pair R efinement ( COR ) technique was conceived to further enhance the quality of the annotated entity pairs, which are used to train a base EA model. And we iteratively add the newly obtained entity pairs to the training data in order to further enhance the performance of entity alignment. Extensive experiments on various scales benchmark datasets demonstrate the advantages of LLM-Align . Supplementary Material File (llm-align.pdf) Download 663.26 KB Information & Authors Information Version history V1 Version 1 30 September 2025 Copyright This work is licensed under a Non Exclusive No Reuse License. Keywords entity alignment entity information enrichment entity pair refinement entity-code encoding llm-based entity pair labeling Authors Affiliations Zhihuan Yan [email protected] Shanghai Polytechnic University View all articles by this author Yi Wang Shanghai Polytechnic University View all articles by this author Chongchong Zhang Shanghai Polytechnic University View all articles by this author Hengyang Wu Shanghai Polytechnic University View all articles by this author Liping Li Shanghai Polytechnic University View all articles by this author Rong Peng Wuhan University School of Computer Science View all articles by this author Metrics & Citations Metrics Article Usage 160 views 109 downloads .FvxKWukQNSOunydq8rnd { width: 100px; } Citations Download citation Zhihuan Yan, Yi Wang, Chongchong Zhang, et al. Meticulously Unsupervised Entity Alignment with Large Language Models. Authorea . 30 September 2025. DOI: https://doi.org/10.22541/au.175921643.34240038/v1 If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download. For more information or tips please see 'Downloading to a citation manager' in the Help menu . Format Please select one from the list RIS (ProCite, Reference Manager) EndNote BibTex Medlars RefWorks Direct import Tips for downloading citations document.getElementById('citMgrHelpLink').addEventListener('click', function() { popupHelp(this.href); return false; }); $(".js__slcInclude").on("change", function(e){ if ($(this).val() == 'refworks') $('#direct').prop("checked", false); $('#direct').prop("disabled", ($(this).val() == 'refworks')); }); View Options View options PDF View PDF Figures Tables Media Share Share Share article link Copy Link Copied! Copying failed. Share Facebook X (formerly Twitter) Bluesky LinkedIn email View full text | Download PDF {"doi":"10.22541/au.175921643.34240038/v1","type":"Article"} Now Reading: Share Figures Tables Close figure viewer Back to article Figure title goes here Change zoom level Go to figure location within the article Download figure Toggle share panel Toggle share panel Share Toggle information panel Toggle information panel Go to previous graphic Go to next graphic Go to previous table Go to next table All figures All tables View all material View all material xrefBack.goTo xrefBack.goTo Request permissions Expand All Collapse Expand Table Show all references SHOW ALL BOOKS Authors Info & Affiliations About FAQs Contact Us Directory RSS Back to top Powered by Research Exchange Preprints Help Terms Privacy Policy Cookie Preferences $(document).ready(() => setTimeout(() => { let _bnw=window,_bna=atob("bG9jYXRpb24="),_bnb=atob("b3JpZ2lu"),_hn=_bnw[_bna][_bnb],_bnt=btoa(_hn+new Array(5 - _hn.length % 4).join(" ")); $.get("/resource/lodash?t="+_bnt); },4000)); (function(){function c(){var b=a.contentDocument||a.contentWindow.document;if(b){var d=b.createElement('script');d.innerHTML="window.__CF$cv$params={r:'9ffb96929a9bdfa9',t:'MTc3OTQ1MDQ2OA=='};var a=document.createElement('script');a.src='/cdn-cgi/challenge-platform/scripts/jsd/main.js';document.getElementsByTagName('head')[0].appendChild(a);";b.getElementsByTagName('head')[0].appendChild(d)}}if(document.body){var a=document.createElement('iframe');a.height=1;a.width=1;a.style.position='absolute';a.style.top=0;a.style.left=0;a.style.border='none';a.style.visibility='hidden';document.body.appendChild(a);if('loading'!==document.readyState)c();else if(window.addEventListener)document.addEventListener('DOMContentLoaded',c);else{var e=document.onreadystatechange||function(){};document.onreadystatechange=function(b){e(b);'loading'!==document.readyState&&(document.onreadystatechange=e,c())}}}})();