{"id":642,"date":"2025-07-15T19:26:15","date_gmt":"2025-07-15T19:26:15","guid":{"rendered":"https:\/\/ccds.ai\/?p=642"},"modified":"2025-08-10T18:15:10","modified_gmt":"2025-08-10T18:15:10","slug":"knowledge-graph-and-llms-based-qa-system","status":"publish","type":"post","link":"https:\/\/ccds.ai\/?p=642","title":{"rendered":"Knowledge Graph and LLMs based QA System"},"content":{"rendered":"<div id='av_section_1'  class='avia-section av-av_section-4626b8e4cec458b6915ec5d17cf7764f main_color avia-section-default avia-no-border-styling  avia-builder-el-0  avia-builder-el-no-sibling  avia-bg-style-scroll container_wrap fullsize'  ><div class='container av-section-cont-open' ><main  role=\"main\" itemprop=\"mainContentOfPage\"  class='template-page content  av-content-full alpha units'><div class='post-entry post-entry-type-page post-entry-642'><div class='entry-content-wrapper clearfix'>\n<section  class='av_textblock_section av-md4xag2r-5630b7d464394cbf944af19207377012'  itemscope=\"itemscope\" itemtype=\"https:\/\/schema.org\/BlogPosting\" itemprop=\"blogPost\" ><div class='avia_textblock'  itemprop=\"text\" ><p>The emergence of advanced large language models (LLMs), such as GPT-4 and LLaMa, marks a significant shift in information retrieval and Question Answering (QA) systems. Unlike traditional keyword-focused searches, these models can generate texts that are more intuitive and human-like. Trained on huge amounts of data, these models apparently \u201cunderstand\u201d the subtleties of language, context, and user intent.\u00a0 However, LLMs have a few significant limitations \u2013 the models may \u201challucinate\u201dand they have limited domain knowledge, common sense etc.. Knowledge Graphs (KGs) can help overcome some of these challenges by providing a structured representation of domain knowledge. A KG is a database that stores information in the form of a graph, with nodes representing entities and edges representing relationships between them. KGs can enhance the reasoning ability of LLMs for QA systems by providing context, domain knowledge related to the questions. In this research, we focus on extracting the domain-specific knowledge sub-graph and enhancing its representation using graph neural networks for solving QA tasks with LLMs.<\/p>\n<\/div><\/section>\n\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":2,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"_jetpack_memberships_contains_paid_content":false,"footnotes":""},"categories":[88],"tags":[],"class_list":["post-642","post","type-post","status-publish","format-standard","hentry","category-ai_ml_projects"],"acf":[],"jetpack_featured_media_url":"","jetpack_sharing_enabled":true,"_links":{"self":[{"href":"https:\/\/ccds.ai\/index.php?rest_route=\/wp\/v2\/posts\/642","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/ccds.ai\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/ccds.ai\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/ccds.ai\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/ccds.ai\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=642"}],"version-history":[{"count":1,"href":"https:\/\/ccds.ai\/index.php?rest_route=\/wp\/v2\/posts\/642\/revisions"}],"predecessor-version":[{"id":643,"href":"https:\/\/ccds.ai\/index.php?rest_route=\/wp\/v2\/posts\/642\/revisions\/643"}],"wp:attachment":[{"href":"https:\/\/ccds.ai\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=642"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/ccds.ai\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=642"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/ccds.ai\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=642"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}