{"id":6611,"date":"2025-09-04T15:55:05","date_gmt":"2025-09-04T13:55:05","guid":{"rendered":"https:\/\/bdva.eu\/?post_type=blog&#038;p=6611"},"modified":"2025-09-04T16:25:29","modified_gmt":"2025-09-04T14:25:29","slug":"neuro-symbolic-ai","status":"publish","type":"blog","link":"https:\/\/bdva.eu\/blog\/neuro-symbolic-ai\/","title":{"rendered":"Neuro-symbolic AI: The key to truly intelligent systems"},"content":{"rendered":"<p><em><strong>Author: <a href=\"https:\/\/nl.linkedin.com\/in\/larryswanson\">Larry Swanson<\/a> (<a href=\"https:\/\/metaphacts.com\/\">metaphacts<\/a> Community Growth Manager) and <a href=\"https:\/\/de.linkedin.com\/in\/phaase\">Peter Haase <\/a>(<a href=\"https:\/\/metaphacts.com\/\">metaphacts<\/a> Founder &amp; Director)<\/strong><\/em><\/p>\n<p>Nearly three years after ChatGPT\u2019s launch in November of 2022, enterprises still struggle to get accurate, reliable and trustworthy outputs from generative AI.<\/p>\n<p>Enterprises that have tried using LLMs to optimise important business processes or support critical business decision-making keep running into now-familiar roadblocks:<\/p>\n<ul>\n<li>search tools that deliver factually incorrect information<\/li>\n<li>analytics platforms that give unreliable and inaccurate reports<\/li>\n<li>conversational AI agents that dismay customers with their sycophancy and untrustworthy answers<\/li>\n<\/ul>\n<p>These are among the reasons that many enterprises are still struggling to unlock the value in their AI investments and why many are revisiting their AI architecture strategies.<\/p>\n<p>To be fair, many of these shortcomings aren\u2019t the fault of LLMs. Generative AI is designed specifically to fabricate answers and the hallucinations for which LLMs are so well known are just a side effect of this feature. Anyone who has worked with these systems knows that you can\u2019t prompt, fine-tune or guardrail your way through these problems. They are inherent in the technology.<\/p>\n<p>So, how can enterprises finally realise the promise of AI and get the factually accurate, trustworthy answers that they and their customers need?<\/p>\n<p>The answer is \u201c<a href=\"https:\/\/youtu.be\/XbtuqqF1MHU\">neuro-symbolic AI.<\/a>\u201d That is, systems that combine neural-network technology like LLMs with symbolic technology like knowledge graphs.<\/p>\n<p>LLMs offer human-friendly natural-language and powerful predictive and generative abilities. Knowledge graphs add conceptual understanding of an enterprise\u2019s unique capabilities and knowledge.<\/p>\n<p>Much like the two systems in Daniel Kahneman&#8217;s &#8220;Thinking, Fast and Slow,&#8221; these two technical paradigms work together to create a fully functioning, more intelligent &#8220;brain&#8221; for your organisation.<\/p>\n<p>Table of Contents<\/p>\n<ul>\n<li><a href=\"#_hd9mdg7g4ymz\">Neuro-symbolic AI is not new<\/a>\n<ul>\n<li><a href=\"#_hfd9pd6r9f2q\">The power of semantic meaning<\/a><\/li>\n<\/ul>\n<\/li>\n<li><a href=\"#_itcr5ps64h6d\">Better together: Knowledge Graphs and LLMs<\/a><\/li>\n<li><a href=\"#_e62kgfsqkzua\">Putting it all together<\/a><\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<h3>Neuro-symbolic AI is not new<\/h3>\n<p>The launch of ChatGPT brought generative AI into the spotlight, but AI as a field has been around for decades, long before <a href=\"https:\/\/www.google.com\/url?q=https:\/\/commons.wikimedia.org\/wiki\/File:IBM_Watson_w_Jeopardy.jpg&amp;sa=D&amp;source=docs&amp;ust=1754396798912352&amp;usg=AOvVaw1h6VqxJUDqEsFjIZweg4h0\">IBM\u2019s Watson appeared on Jeopardy<\/a> and Deep Blue beat chess grandmaster Garry Kasparov. The machine learning and other neural-network methods that power generative AI and LLMs date back to the 1940s, while symbolic AI arose in the 1950s|\u2014 and many AI practitioners have been integrating these two technology paradigms since the 1990s. So it\u2019s not like people have been overlooking these technologies. It\u2019s just that recent advances in computing power and AI methods have given them both new importance and significance.<\/p>\n<p>LLMs are great at what they do because they are trained on vast amounts of data gleaned from a variety of sources. When you need to make a decision for your company or provide an answer about one of your enterprise\u2019s products or services, though, general knowledge of the world, while helpful, is not sufficient. And, while it is possible to train and fine-tune LLMs with your enterprise data, only symbolic AI can contextualise and deliver your enterprise\u2019s precise, unique knowledge.<\/p>\n<p>Symbolic AI is the explicit representation of knowledge. It captures the facts about an enterprise and the knowledge it has accumulated and stores them in a way that both computers and humans can understand and use. It\u2019s the use of universally understood symbols \u2013 numbers, words, logical expressions, etc. \u2013 that gives this type of AI its unique power. While LLMs, on the other hand, can offer remarkably plausible predictions based on their statistical analysis of what has been shared on the web and elsewhere, only symbolic AI, like a <a href=\"https:\/\/metaphacts.com\/what-is-a-knowledge-graph\">semantic knowledge graph<\/a>, can deliver facts and knowledge that are grounded in the actual activities that an enterprise does and the wisdom its employees have accumulated.<\/p>\n<p>As distinct as these two components of neuro-symbolic AI are, each can exhibit elements of the other. For example, LLMs can be trained on enterprise data to better inform their outputs. And implementations like the <a href=\"https:\/\/www.wikidata.org\/wiki\/Wikidata:Main_Page\">Wikidata<\/a> project show how symbolic AI can be used to represent general facts about the world. This explains why some have used the yin-yang image to illustrate the concept of neuro-symbolic AI.<\/p>\n<p><img decoding=\"async\" class=\"alignnone size-full wp-image-6614 lazyload\" src=\"data:image\/gif;base64,R0lGODlhAQABAIAAAAAAAP\/\/\/yH5BAEAAAAALAAAAAABAAEAAAIBRAA7\" data-src=\"https:\/\/bdva.eu\/wp-content\/uploads\/2025\/09\/Yin-Yang.png\" alt=\"\" width=\"210\" height=\"210\" \/><noscript><img decoding=\"async\" class=\"alignnone size-full wp-image-6614 lazyload\" src=\"https:\/\/bdva.eu\/wp-content\/uploads\/2025\/09\/Yin-Yang.png\" alt=\"\" width=\"210\" height=\"210\" srcset=\"https:\/\/bdva.eu\/wp-content\/uploads\/2025\/09\/Yin-Yang.png 210w, https:\/\/bdva.eu\/wp-content\/uploads\/2025\/09\/Yin-Yang-150x150.png 150w\" sizes=\"(max-width: 210px) 100vw, 210px\" \/><\/noscript><\/p>\n<p>&nbsp;<\/p>\n<h3>The power of semantic meaning<\/h3>\n<p>One of the most impactful aspects of symbolic AI is its ability to give semantic meaning to the information it works with. The symbols that are used to represent real-world entities can be defined, connected and otherwise contextualised so that both humans and computers can truly understand the concepts represented by the symbols. So when an analyst asks a knowledge graph about \u201cnew customer orders in Q3,\u201d the system has the information it needs to understand how the enterprise defines a \u201cnew\u201d customer, what constitutes an \u201corder,\u201d and the time span for the third quarter in their fiscal calendar.<\/p>\n<p>LLMs can approximate semantic understanding by looking at which words and tokens appear close to one another in vector space, but only human-vetted knowledge ensconced in a symbolic AI system can deliver consistent answers that align with an enterprise\u2019s actual practices and precise language. In the last example, for instance, if your enterprise has adopted an unconventional fiscal year, an LLM might assume a conventional January-through-December fiscal year, completely missing the meaning of \u201cQ3\u201d in your organisation.<\/p>\n<p>One powerful implication of this clear articulation of business information in a knowledge system is the ability to create a \u201csemantic layer,\u201d an <a href=\"https:\/\/www.youtube.com\/watch?v=tN_FD_0R0sA\">enterprise information architecture<\/a> concept that lets an organisation understand and connect its business processes, technical objects and data and information. This ability to access semantic understanding lets enterprises streamline and accelerate their business processes and make crucial business decisions more quickly, giving them an almost unfair competitive advantage. As one <a href=\"https:\/\/www.linkedin.com\/posts\/tonyseale_semantics-is-the-latest-buzzword-in-tech-activity-7354420244217569281-4s58\/\">industry expert recently observed<\/a> about the emerging ubiquity of AI, \u201cIf everything becomes intelligent, then meaning becomes the differentiator.\u201d<\/p>\n<p>&nbsp;<\/p>\n<h3>Better together: Knowledge Graphs and LLMs<\/h3>\n<p>As you evaluate the strengths and weaknesses of each of these technologies, their complementary benefits become more clear. At the highest level, LLMs and other neural-network technology are really good at <strong>learning<\/strong>, while knowledge graphs and other symbolic AI technology are good at <strong>knowing<\/strong>.<\/p>\n<p>LLMs are very good at learning to identify patterns, make predictions and generate outputs. They do this by looking at huge repositories of information, breaking it down into mathematically computable elements and reassembling those elements into statistically plausible words, images and recordings. This learning doesn\u2019t lead to actual knowledge that the LLM can use later. You can see this when you ask an LLM the same question and get a slightly (sometimes significantly) different answer each time you run the query. This reliance on statistical computation is why these systems are called \u201cblack boxes.\u201d Not even the engineers who designed them can get them to explain their actions. This lack of transparency and explainability has been an obstacle to enterprises trying to build trustworthy AI systems.<\/p>\n<p>Knowledge graphs capture and expose the things that an enterprise actually knows\u2014its business practices, its policies and procedures, its customers and suppliers, its products and services, its data and other digital assets, and even the tacit knowledge in its employees\u2019 heads. This knowledge is unique to any one enterprise. In fact, it\u2019s arguably any enterprise\u2019s most important asset. Unlike the general information captured at one point in time that an LLM works with, the enterprise-specific information in a knowledge graph is always up to date and accurate.<\/p>\n<p>Until recently, building knowledge graphs strained the capabilities of most enterprises, but in a serendipitous turn of events, it turns out that LLMs can help build these sophisticated knowledge systems. LLMs\u2019 natural-language interfaces, predictive power and generative abilities help knowledge engineers by automating labor-intensive tasks like entity extraction, accelerating ontology building and improving the quality of the data in the graph. With the help of generative AI, knowledge graphs are now accessible to many more enterprises.<\/p>\n<p>It also turns out that knowledge graphs can help LLMs. Their authoritative, human-vetted knowledge of an enterprise\u2019s unique capabilities and knowledge can address the transparency, accuracy and other trust issues that arise with unreliable LLM outputs.<\/p>\n<p>&nbsp;<\/p>\n<h3>Putting it all together<\/h3>\n<p>Neuro-symbolic AI is where these complementary capabilities come together. Just as you wouldn\u2019t bring only half of your brain to work, enterprises shouldn\u2019t bring just one half of artificial intelligence\u2019s capabilities to their enterprise architectures. So, if your enterprise is not already exploring how knowledge graphs and symbolic AI can augment your organisation\u2019s intelligence\u2014both artificial and actual\u2014now is a good time to start.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Get practical insights into how knowledge graphs can elevate the trustworthiness and explainability of AI systems by discussing real-world use cases. Learn how knowledge graphs can tackle pressing challenges.<\/p>\n","protected":false},"featured_media":6612,"template":"","blog-category":[138,141],"blog-tags":[151,158,157,156,159],"class_list":["post-6611","blog","type-blog","status-publish","has-post-thumbnail","hentry","blog-category-ai","blog-category-ai-application","blog-tags-ai","blog-tags-intelligent-systems","blog-tags-neuro","blog-tags-neuro-symbolic","blog-tags-system"],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v26.9 - https:\/\/yoast.com\/product\/yoast-seo-wordpress\/ -->\n<title>Neuro-symbolic AI: The key to truly intelligent systems - BDV Big Data Value Association<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/bdva.eu\/blog\/neuro-symbolic-ai\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Neuro-symbolic AI: The key to truly intelligent systems - BDV Big Data Value Association\" \/>\n<meta property=\"og:description\" content=\"Get practical insights into how knowledge graphs can elevate the trustworthiness and explainability of AI systems by discussing real-world use cases. Learn how knowledge graphs can tackle pressing challenges.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/bdva.eu\/blog\/neuro-symbolic-ai\/\" \/>\n<meta property=\"og:site_name\" content=\"BDV Big Data Value Association\" \/>\n<meta property=\"article:modified_time\" content=\"2025-09-04T14:25:29+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/bdva.eu\/wp-content\/uploads\/2025\/09\/BDVA-blog_Neuro-symbolic-AI-The-key-to-truly-intelligent-systems-1024x576.png\" \/>\n\t<meta property=\"og:image:width\" content=\"1024\" \/>\n\t<meta property=\"og:image:height\" content=\"576\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/png\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:label1\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data1\" content=\"7 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\/\/schema.org\",\"@graph\":[{\"@type\":\"WebPage\",\"@id\":\"https:\/\/bdva.eu\/blog\/neuro-symbolic-ai\/\",\"url\":\"https:\/\/bdva.eu\/blog\/neuro-symbolic-ai\/\",\"name\":\"Neuro-symbolic AI: The key to truly intelligent systems - BDV Big Data Value Association\",\"isPartOf\":{\"@id\":\"https:\/\/bdva.eu\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/bdva.eu\/blog\/neuro-symbolic-ai\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/bdva.eu\/blog\/neuro-symbolic-ai\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/bdva.eu\/wp-content\/uploads\/2025\/09\/BDVA-blog_Neuro-symbolic-AI-The-key-to-truly-intelligent-systems.png\",\"datePublished\":\"2025-09-04T13:55:05+00:00\",\"dateModified\":\"2025-09-04T14:25:29+00:00\",\"breadcrumb\":{\"@id\":\"https:\/\/bdva.eu\/blog\/neuro-symbolic-ai\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/bdva.eu\/blog\/neuro-symbolic-ai\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/bdva.eu\/blog\/neuro-symbolic-ai\/#primaryimage\",\"url\":\"https:\/\/bdva.eu\/wp-content\/uploads\/2025\/09\/BDVA-blog_Neuro-symbolic-AI-The-key-to-truly-intelligent-systems.png\",\"contentUrl\":\"https:\/\/bdva.eu\/wp-content\/uploads\/2025\/09\/BDVA-blog_Neuro-symbolic-AI-The-key-to-truly-intelligent-systems.png\",\"width\":1600,\"height\":900},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/bdva.eu\/blog\/neuro-symbolic-ai\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/bdva.eu\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Blog\",\"item\":\"https:\/\/bdva.eu\/blog\/\"},{\"@type\":\"ListItem\",\"position\":3,\"name\":\"Neuro-symbolic AI: The key to truly intelligent systems\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/bdva.eu\/#website\",\"url\":\"https:\/\/bdva.eu\/\",\"name\":\"Big Data Value Association\",\"description\":\"BDVA is an industry-driven research and innovation organisation with a mission to develop an innovation ecosystem that enables the AI and data-driven digital transformation of the economy and society in Europe.\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/bdva.eu\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Neuro-symbolic AI: The key to truly intelligent systems - BDV Big Data Value Association","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/bdva.eu\/blog\/neuro-symbolic-ai\/","og_locale":"en_US","og_type":"article","og_title":"Neuro-symbolic AI: The key to truly intelligent systems - BDV Big Data Value Association","og_description":"Get practical insights into how knowledge graphs can elevate the trustworthiness and explainability of AI systems by discussing real-world use cases. Learn how knowledge graphs can tackle pressing challenges.","og_url":"https:\/\/bdva.eu\/blog\/neuro-symbolic-ai\/","og_site_name":"BDV Big Data Value Association","article_modified_time":"2025-09-04T14:25:29+00:00","og_image":[{"width":1024,"height":576,"url":"https:\/\/bdva.eu\/wp-content\/uploads\/2025\/09\/BDVA-blog_Neuro-symbolic-AI-The-key-to-truly-intelligent-systems-1024x576.png","type":"image\/png"}],"twitter_card":"summary_large_image","twitter_misc":{"Est. reading time":"7 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/bdva.eu\/blog\/neuro-symbolic-ai\/","url":"https:\/\/bdva.eu\/blog\/neuro-symbolic-ai\/","name":"Neuro-symbolic AI: The key to truly intelligent systems - BDV Big Data Value Association","isPartOf":{"@id":"https:\/\/bdva.eu\/#website"},"primaryImageOfPage":{"@id":"https:\/\/bdva.eu\/blog\/neuro-symbolic-ai\/#primaryimage"},"image":{"@id":"https:\/\/bdva.eu\/blog\/neuro-symbolic-ai\/#primaryimage"},"thumbnailUrl":"https:\/\/bdva.eu\/wp-content\/uploads\/2025\/09\/BDVA-blog_Neuro-symbolic-AI-The-key-to-truly-intelligent-systems.png","datePublished":"2025-09-04T13:55:05+00:00","dateModified":"2025-09-04T14:25:29+00:00","breadcrumb":{"@id":"https:\/\/bdva.eu\/blog\/neuro-symbolic-ai\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/bdva.eu\/blog\/neuro-symbolic-ai\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/bdva.eu\/blog\/neuro-symbolic-ai\/#primaryimage","url":"https:\/\/bdva.eu\/wp-content\/uploads\/2025\/09\/BDVA-blog_Neuro-symbolic-AI-The-key-to-truly-intelligent-systems.png","contentUrl":"https:\/\/bdva.eu\/wp-content\/uploads\/2025\/09\/BDVA-blog_Neuro-symbolic-AI-The-key-to-truly-intelligent-systems.png","width":1600,"height":900},{"@type":"BreadcrumbList","@id":"https:\/\/bdva.eu\/blog\/neuro-symbolic-ai\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/bdva.eu\/"},{"@type":"ListItem","position":2,"name":"Blog","item":"https:\/\/bdva.eu\/blog\/"},{"@type":"ListItem","position":3,"name":"Neuro-symbolic AI: The key to truly intelligent systems"}]},{"@type":"WebSite","@id":"https:\/\/bdva.eu\/#website","url":"https:\/\/bdva.eu\/","name":"Big Data Value Association","description":"BDVA is an industry-driven research and innovation organisation with a mission to develop an innovation ecosystem that enables the AI and data-driven digital transformation of the economy and society in Europe.","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/bdva.eu\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"}]}},"_links":{"self":[{"href":"https:\/\/bdva.eu\/wp-json\/wp\/v2\/blog\/6611","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/bdva.eu\/wp-json\/wp\/v2\/blog"}],"about":[{"href":"https:\/\/bdva.eu\/wp-json\/wp\/v2\/types\/blog"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/bdva.eu\/wp-json\/wp\/v2\/media\/6612"}],"wp:attachment":[{"href":"https:\/\/bdva.eu\/wp-json\/wp\/v2\/media?parent=6611"}],"wp:term":[{"taxonomy":"blog-category","embeddable":true,"href":"https:\/\/bdva.eu\/wp-json\/wp\/v2\/blog-category?post=6611"},{"taxonomy":"blog-tags","embeddable":true,"href":"https:\/\/bdva.eu\/wp-json\/wp\/v2\/blog-tags?post=6611"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}