GraphNews

Seven knowledge graph quality problems that undermine GraphRAG performance and how to detect them

What they mean, what they don’t, and how to use them

Citation metrics are widely used to assess academic impact but suffer from social biases, including institutional prestige and journal visibility. Here we introduce rXiv Semantic Impact (XSI), a...

In an era where software systems are increasingly complex and interconnected, effectively managing the relationships between packages, maintainers, dependencies, and vulnerabilities is both a challenge and a necessity. This paper explores the integration of knowledge graphs into the Debian ecosystem as a powerful means to bring structure, semantics, and coherence to diverse sources of package-related data. By unifying information such as package metadata, security advisories, and reproducibility reports into a single graph-based representation, we enable richer visibility into the ecosystem's structure and behavior. Beyond constructing the DebKG graph, we demonstrate how it supports practical, high-impact applications — such as tracing vulnerability propagation and identifying gaps between community needs and development activity — thereby offering a foundation for smarter, data-informed decision-making within Debian.

Wikidata Knowledge Graph to Enable Equitable and Validated Generative AI - Jonathan Fraine & Lydia Pintscher, Wikimedia DeutschlandGenerative AI has changed ...

AbstractMotivation. Ecological systems are complex. Representing heterogeneous knowledge about ecological systems is a pervasive challenge because data are

Earlier this week I came across a post by Miklós Molnár that sparked something I think the ontology community has needed to articulate for a long time. The post described a shift in how we might think about ontology mapping and alignment in the age of AI.

The ultimate RAG for your monorepo. Query, understand, and edit multi-language codebases with the power of AI and knowledge graphs - vitali87/code-graph-rag

What is your role? I am a product manager in the Office of the CTO at Bloomberg, where I am responsible for developing products that help to deploy semantic solutions that facilitate our data integration and delivery. Bloomberg is a global provider of financial news and information, including real-t

OpenAI’s recent paper, Why Language Models Hallucinate, takes direct aim at one of the most persistent criticisms of AI: hallucination. The research makes a clear point: hallucinations are not random glitches.

Calling all data scientists, developers, and managers! 📢 Looking to level up your team's knowledge of graph technology? We're excited to share the recorded 2-part training series, "Graph Tech Demystified" with the amazing Paco Nathan. This is your chance to get up to speed on graph fundamentals: In Part 1: Intro to Graph Technologies, you'll learn: - Core concepts in graph tech. - Common pitfalls and what graph technology won't solve. - Focus of graph analytics and measuring quality. 🎥 Recording https://lnkd.in/gCtCCZH5 📖 Slides https://lnkd.in/gbCnUjQN In Part 2: Advanced Topics in Graph Technologies, we explore: - Sophisticated graph patterns like motifs and probabilistic subgraphs. - Intersection of Graph Neural Networks (GNNs) and Reinforcement Learning. - Multi-agent systems and Graph RAG. 🎥 Recording https://lnkd.in/g_5B8nNC 📖 Slides https://lnkd.in/g6iMbJ_Z Insider tip: The resources alone are enough to keep you busy far longer the time it takes to watch the training!

AI data processing-related companies have seen continuous growth in financing in recent years, representing essential AI subdivision…

Unlock true AI potential with neuro-symbolic AI. Learn how combining LLMs with knowledge graphs solves unreliable and inaccurate outputs for enterprise success.

What is an ontology? Well it depends on who’s talking. Ontology talk has sprung up a lot in data circles the last couple of years. You may have read in the news that the Department of Defense adopted an ontology, Juan will tell you enterprise AI needs an ontology, Jessica will tell you how to build an ontology pipeline, and Palantir will gladly sell you one (🤦‍♂️). Few people actually spell out what they mean when talking about “ontology” and unsurprisingly they’re not all talking about the same thing. Ontology is a borrow word for information scientists who took it from philosophy where ontology is an account of the fundamental things around us. Some of you no doubt read Plato’s Republic with the allegory of the cave, which introduces the theory of forms. Aristotle’s had two ontologies, one in the Categories and another in the Metaphysics. (My friend Jessica would call the former a Taxonomy). When I talk about ontology as a philosopher I’m interested in the fundamental nature or reality. Is it made up of medium sized dry goods or subatomic wave functions. Information scientists aren’t interested in the fundamental nature of reality, but they are interested in how we organize our data about reality. So when they talk about ontologies they actually mean one of several different technologies. When Juan talks about ontologies I know in my head he means knowledge graphs. This introduces a regression because knowledge graphs can be implemented in number of different ways, though the Resource Description Framework (RDF) is probably the most popular. If you’ve ever built a website, RDF will look familiar because it’s simply URIs that represent subject predicate object triples. (Juan-works at-ServiceNow) Because we’re technologists there are a number of different ways to represent, store, and query a knowledge graph. (See XKCD 927) Knowledge graphs are cool and all, but they’re not the only approach to ontologies. When the DoD went shopping for an ontology, they started with an upper formal ontology, specifically the Basic Formal Ontology. I think BFO is cool if only because it’s highly influenced by philosophy through the work of philosopher Barry Smith (Buffalo). Formal ontologies can organize the concepts, relations, axioms, across large domains like healthcare, but they’re best fit for slowly evolving industries. While BFO might be the most popular upper ontology it’s certainly not the only one on the market. My own view is that in data we’re all engaged in ontological work in a broad sense. If you’re building a data model, you need a good account of “what there is” for the business domain. At what grain do we count inventory? Bottles, cases, pallets, etc? The more specific we get around doing ontological work, the harder the deliverables become. eg knowledge graphs are harder to build than data models, formal ontologies are harder to build than knowledge graphs. Most organizations need good data models over formal ontologies. | 109 comments on LinkedIn

A database tells you what is connected. A knowledge graph tells you why. → SQL hides semantics in schema logic. Foreign keys don’t explain relationships, they just enforce them. → Knowledge graphs make relationships explicit. Edges have meaning, context, synonyms, hierarchies. → Traversal in SQL = JOIN gymnastics. Traversal in a KG = natural multi-hop reasoning. Benchmarks show LLMs answered enterprise questions correctly 16.7% of the time over SQL … vs. 54.2% over the same data in a KG. Same data, different representation. Sure, you can bolt ontologies, synonyms, and metadata onto SQL. But at that point, you’ve basically reinvented a knowledge graph. So the real question is: Do you want storage, or do you want reasoning? #KnowledgeGraphs #AI #LLM #Agents #DataEngineering | 51 comments on LinkedIn

This post captures the desire for a short cut to #KnowledgeGraphs, the inability of #LLMs to reliably generate #StructuredKnowledge, and the lengths folks will go to realize even basic #semantic queries (the author manually encoded 1,000 #RDF triples, but didn’t use #OWL). https://lnkd.in/eJE_27gS #Ontologists by nature are generally rigorous, if not a tad bit pedantic, as they seek to structure #domain knowledge. 25 years of #SemanticWeb and this is still primarily a manual, tedious, time-consuming and error-prone process. In part, #DeepLearning is a reaction to #structured, #labelled, manually #curated #data (#SymbolicAI). When #GenAI exploded on the scene a couple of years ago, #Ontologist were quick to note the limitations of LLMs. Now some #Ontologists are having a "Road to Damascus" moment - they are aspirationally looking to Language Models as an interface for #Ontologies to lower barrier to ontology creation and use, which are then used for #GraphRAG, but this is a circular firing squad given the LLM weaknesses they have decried. This isn't a solution, it's a Hail Mary. They are lowering the standards on quality and setting up the even more tedious task of identifying non-obvious, low-level LLM errors in an #Ontology (same issue Developers have run into with LLM CodeGen - good for prototypes, not for production code). The answer is not to resign ourselves and subordinate ontologies to LLMs, but to take the high-road using #UpperOntologies to ease and speed the design, use and maintenance of #KGs. An upper ontology is a graph of high-level concepts, types and policies independent of a specific #domain implementation. It provides an abstraction layer with re-usable primitives, building blocks and services that streamline and automate domain modeling tasks (i.e., a #DSL for DSLs). Importantly, an upper ontology drives well-formed and consistent objects and relationships and provides for governance (e.g., security/identity, change management). This is what we do EnterpriseWeb. #Deterministic, reliable, trusted ontologies should be the center of #BusinessArchitecture, not a side-car to an LLM.

Apache TinkerPop™ is a graph computing framework for graph systems and the home of the Gremlin graph traversal language. Contributorcasts allow contributors ...

A canonical problem in computer science is to find the shortest route to every point in a network. A new approach beats the classic algorithm taught in textbooks.

NLWeb turns Schema Markup into AI-ready data—unlocking smarter search, improved content discoverability, and faster AI integration.

Every knowledge system has to wrestle with a deceptively simple question: what do we assert, and what do we derive? That line between assertion and derivation is where Object-Role Modeling (ORM) and the Resource Description Framework (RDF) with the Web Ontology Language (OWL) go in radically differe

Enterprise Adoption of GraphRAG: The CRUD Challenge GraphRAG and other retrieval-augmented generation (RAG) workflows are currently attracting a lot of attention. Their prototypes are impressive, with data ingestion, embedding generation, knowledge graph creation, and answer generation all functioning smoothly. However, without proper CRUD (Create, Read, Update, Delete) support, these systems are limited to academic experimentation rather than becoming enterprise-ready solutions. Update: knowledge is constantly evolving. Regulations change, medical guidelines are updated, and product catalogues are revised. If a system cannot reliably update its information, it will produce outdated answers and quickly lose credibility. Delete: Incorrect or obsolete information must be deleted. In regulated industries such as healthcare, finance and law, retaining deleted data can lead to compliance issues. Without a deletion mechanism, incorrect or obsolete information can persist in the system long after it should have been removed. This is an issue that many GraphRAG pilots face. Although the proof of concept looks promising, limitations become evident when someone asks, "What happens when the source of truth changes?" While reading and creation are straightforward, updates and deletions determine whether a system remains a prototype or becomes a reliable enterprise tool. Most implementations stop at 'reading', and while retrieval and answer generation work, real-world enterprise systems never stand still. In order for GraphRAG and RAG in general to transition from research labs to widespread enterprise adoption, support for CRUD must be an fundamental aspect of the design process. #GraphRAG #RAG #KnowledgeGraph #EnterpriseAI #CRUD #EnterpriseAdoption #TrustworthyAI #DataManagement

🎥 𝗧𝗵𝗲 𝗳𝗶𝗹𝗺 𝘁𝗵𝗮𝘁’𝘀 𝗮𝗯𝗼𝘂𝘁 𝘁𝗼 𝘄𝗶𝗻 𝗩𝗲𝗻𝗶𝗰𝗲? 𝗟𝗲𝘁'𝘀 𝗺𝗮𝗽 𝗶𝘁 𝗶𝗻 𝗮 𝗞𝗻𝗼𝘄𝗹𝗲𝗱𝗴𝗲 𝗚𝗿𝗮𝗽𝗵 Just asked 𝗔𝗴𝗲𝗻𝘁 𝗪𝗼𝗿𝗱𝗟𝗶𝗳𝘁 to retrieve the 𝑮𝒐𝒐𝒈𝒍𝒆 𝑲𝒏𝒐𝒘𝒍𝒆𝒅𝒈𝒆 𝑮𝒓𝒂𝒑𝒉 details for "𝑵𝒐 𝑶𝒕𝒉𝒆𝒓 𝑪𝒉𝒐𝒊𝒄𝒆" — the dark comedy thriller by Park Chan-wook that’s leading the Venice buzz. 𝗛𝗲𝗿𝗲 𝘁𝗵𝗲 𝗥𝗲𝘀𝘂𝗹𝘁: ✅ Google KG entity ID: /g/11w2hjvh3j ✅ Wikidata: Q129906152 ✅ Cast, director, source material, and more — in under a second. ✅ Fallback-safe, deeply enriched with attributes from Wikidata. This is Enhanced Entity Research via MCP (Model Context Protocol). ✔️ Pulls data from Google’s Enterprise KG ✔️ Enriches with Wikidata (gender, occupation, relationships, etc.) ✔️ Builds 3–5× richer profiles — instantly ready for clustering, schema, content. 𝗪𝗵𝘆 𝗱𝗼𝗲𝘀 𝗶𝘁 𝗺𝗮𝘁𝘁𝗲𝗿? This is what AI-ready structured data looks like — live, real-time, and grounded. From the Venice Film Festival to your Knowledge Graph in milliseconds. 💥 Don’t let a cascade of incompetence pollute your AI workflows. 💡 Combine structured knowledge with agentic AI to drive precision, context, and trust across multi-step tasks. 👉 Enjoy the artifact (on Claude): https://lnkd.in/dYYMby26 👉 Full workflow: https://lnkd.in/dNHJ_DpP

It's great to see the launch of Google Cloud's new Agentspace Knowledge Graph, built on Spanner Graph. Agentspace Knowledge Graph (https://lnkd.in/gYM6xZQS) allows an AI agent to understand the real-world context of your organization—the web of relationships between people, projects, and products. This is the difference between finding a document and understanding who wrote it, what team they're on, and what project it's for. Because this context is a network, the problem is uniquely suited for a graph model. Spanner Graph (https://lnkd.in/gkwbGFbS) provides a natural way to model this reality, allowing an AI agent to instantly traverse complex connections to find not just data, but genuine insight. This is how we move from AI that finds information to AI that understands it. The ability to reason over the "why" behind the data is a true game-changer. #GoogleCloud #GenAI #Agentspace #SpannerGraph #KnowledgeGraph

Why is ontology engineering such a mess? There's a simple reason: proprietary data models, proprietary inference engines, and proprietary query engines. Some ontology traditions have always been open standards: Prolog/Datalog, RDF, conceptual graphs all spring to mind. However, startups in ontology often take government money, apparently under conditions that inspire them to close their standards. One notable closed-standard ontology vendor is Palantir. If you look into the world of graph databases, you will discover many more vendors operating on closed standards, as well as some vendors who've implemented less popular and in my view less user-friendly open standards. My advice to ontology consultants and to their clients is to prioritize vendors that implement open standards. Given that this list includes heavyweights like Oracle and AWS, it isn't hard to remain within one's comfort zone while embracing open standards. Prolog and RDF are likely the most popular and widely known standards for automated inference, knowledge representation, etc. There are more potential engineers and computer scientists and modelers who've trained on these standards than any vendor you may wish to name with a closed standard, there are prebuilt ontologies and query rewriting approaches and inference engine profiles, there are constraint programming approaches for both, etc. Oracle and AWS have chosen to go with open standards rather than inventing some new graph data model and yet another query processor to handle the same inference and business rule workloads we've been handling with various technologies since the 1950s. Learn from their example, and please quit wasting all of our time on Earth by reinventing the semantic network.

I recently came across some misconceptions about why the LPG graph model is more effective than RDF for GraphRAG, and I wrote this article to debunk them. At the end, I also elaborate on two principal advantages of RDF when it comes to provision of context and grounding to LLMs (i) schema languages

Guy van den Broeck (UCLA)https://simons.berkeley.edu/talks/guy-van-den-broeck-ucla-2025-04-29Theoretical Aspects of Trustworthy AIToday, many expect AI to ta...

Autonomous vehicles (AVs) represent a transformative innovation in transportation, promising enhanced safety, efficiency, and sustainability. Despite these promises, achieving robustness, reliability, and adherence to ethical standards in AV systems remains challenging due to the complexity of integrating diverse technologies. This survey reviews literature from 2017 to 2023, analyzing over 90 papers to explore the integration of knowledge graphs (KGs) into AV technologies. Our findings indicate that KGs significantly enhance AV systems by providing structured semantic understanding, improving real-time decision-making, and ensuring compliance with regulatory standards. The paper identifies that while KGs contribute to better environmental perception and contextual reasoning, challenges remain in their seamless integration with existing systems and in maintaining processing speed. We also address the ethical dimensions of AV decision-making, advocating for frameworks that prioritize safety and transparency. This review underscores the potential of KGs to address critical challenges in AV technologies, offering a hopeful and optimistic outlook for the development of robust, reliable, and socially responsible autonomous transportation solutions.