{"id":16599,"date":"2024-09-20T12:29:05","date_gmt":"2024-09-20T10:29:05","guid":{"rendered":"https:\/\/is.ijs.si\/?p=16599"},"modified":"2025-03-26T13:20:33","modified_gmt":"2025-03-26T12:20:33","slug":"knowledge-graph-extraction-from-textual-data-using-llm","status":"publish","type":"post","link":"https:\/\/is.ijs.si\/?p=16599","title":{"rendered":"Knowledge graph Extraction from Textual data using LLM"},"content":{"rendered":"\n<p>Khasa Gillani, Erik Novak, Klemen Kenda and Dunja Mladeni\u0107<\/p>\n<p><strong>ABSTRACT<\/strong><br \/>The advent of Large Language Models (LLMs), such as Chat-<br \/>GPT and GPT-4, has revolutionized natural language process-<br \/>ing, opening avenues for advanced textual understanding. This<br \/>study explores the application of LLMs in developing Knowledge<br \/>graphs from textual data. Knowledge graphs offer a structured<br \/>representation of information, facilitating enhanced comprehen-<br \/>sion and utilization of unstructured text. We intend to construct<br \/>Knowledge graphs that capture relationships and entities within<br \/>diverse textual datasets by harnessing LLMs\u2019 contextual under-<br \/>standing and language generation capabilities. The primary goal<br \/>is to explore and understand how well LLMs can identify and<br \/>extract relevant entities and relationships from textual data using<br \/>prompt engineering while contributing to structured knowledge<br \/>representation.<\/p>\n<p>\u00a0<\/p>\n\n\n\n<div data-wp-interactive=\"core\/file\" class=\"wp-block-file\"><object data-wp-bind--hidden=\"!state.hasPdfPreview\" hidden class=\"wp-block-file__embed\" data=\"https:\/\/is.ijs.si\/wp-content\/uploads\/2024\/10\/IS2024_-_SIKDD_2024_paper_15-1.pdf\" type=\"application\/pdf\" style=\"width:100%;height:600px\" aria-label=\"Embed of IS2024_-_SIKDD_2024_paper_15-1.\"><\/object><a id=\"wp-block-file--media-2aa68cf9-65c2-497d-99ea-6087c8db99e7\" href=\"https:\/\/is.ijs.si\/wp-content\/uploads\/2024\/10\/IS2024_-_SIKDD_2024_paper_15-1.pdf\">IS2024_-_SIKDD_2024_paper_15-1<\/a><a href=\"https:\/\/is.ijs.si\/wp-content\/uploads\/2024\/10\/IS2024_-_SIKDD_2024_paper_15-1.pdf\" class=\"wp-block-file__button wp-element-button\" download aria-describedby=\"wp-block-file--media-2aa68cf9-65c2-497d-99ea-6087c8db99e7\">Download<\/a><\/div>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":29,"featured_media":24966,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[109,102],"tags":[],"class_list":["post-16599","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-doi-sikdd-2024","category-papers"],"_links":{"self":[{"href":"https:\/\/is.ijs.si\/index.php?rest_route=\/wp\/v2\/posts\/16599","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/is.ijs.si\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/is.ijs.si\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/is.ijs.si\/index.php?rest_route=\/wp\/v2\/users\/29"}],"replies":[{"embeddable":true,"href":"https:\/\/is.ijs.si\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=16599"}],"version-history":[{"count":3,"href":"https:\/\/is.ijs.si\/index.php?rest_route=\/wp\/v2\/posts\/16599\/revisions"}],"predecessor-version":[{"id":25007,"href":"https:\/\/is.ijs.si\/index.php?rest_route=\/wp\/v2\/posts\/16599\/revisions\/25007"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/is.ijs.si\/index.php?rest_route=\/wp\/v2\/media\/24966"}],"wp:attachment":[{"href":"https:\/\/is.ijs.si\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=16599"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/is.ijs.si\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=16599"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/is.ijs.si\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=16599"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}