Large Language Models (LLMs) are revolutionizing the development of AI assistants capable of performing diverse tasks across domains. However, current state-of-the-art LLM-driven agents face...

An open-source Python framework for real-time, graph-based knowledge in Neo4j

How LLMs can used in a knowledge extraction and visualization pipeline

We’re thrilled to announce new Text2Cypher models and Google’s MCP Toolbox for Databases from the collaboration between Google Cloud and Neo4j.

The Model Context Protocol gives users a wide range of services they can connect to from the comfort of their AI client.

Choosing the Right Format: How Knowledge Graph Layouts Impact AI Reasoning ... 👉 Why This Matters Most AI systems blend knowledge graphs (structured data) with large language models (flexible reasoning). But there’s a hidden variable: "how" you translate the graph into text for the AI. Researchers discovered that the formatting choice alone can swing performance by up to "17.5%" on reasoning tasks. Imagine solving 1 in 5 more problems correctly just by adjusting how you present data. 👉 What They Built KG-LLM-Bench is a new benchmark to test how language models reason with knowledge graphs. It includes five tasks: - Triple verification (“Does this fact exist?”) - Shortest path finding (“How are two concepts connected?”) - Aggregation (“How many entities meet X condition?”) - Multi-hop reasoning (“Which entities linked to A also have property B?”) - Global analysis (“Which node is most central?”) The team tested seven models (Claude, GPT-4o, Gemini, Llama, Nova) with five ways to “textualize” graphs, from simple edge lists to structured JSON and semantic web formats like RDF Turtle. 👉 Key Insights 1. Format matters more than assumed:   - Structured JSON and edge lists performed best overall, but results varied by task.   - For example, JSON excels at aggregation tasks (data is grouped by entity), while edge lists help identify central nodes (repeated mentions highlight connections). 2. Models don’t cheat: Replacing real entity names with fake ones (e.g., “France” → “Verdania”) caused only a 0.2% performance drop, proving models rely on context, not memorized knowledge. 3. Token efficiency:   - Edge lists used ~2,600 tokens vs. JSON-LD’s ~13,500. Shorter formats free up context space for complex reasoning.   - But concise ≠ always better: structured formats improved accuracy for tasks requiring grouped data. 4. Models struggle with directionality:   Counting outgoing edges (e.g., “Which countries does France border?”) is easier than incoming ones (“Which countries border France?”), likely due to formatting biases. 👉 Practical Takeaways - Optimize for your task: Use JSON for aggregation, edge lists for centrality. - Test your model: The best format depends on the LLM—Claude thrived with RDF Turtle, while Gemini preferred edge lists. - Don’t fear pseudonyms: Masking real names minimally impacts performance, useful for sensitive data. The benchmark is openly available, inviting researchers to add new tasks, graphs, and models. As AI handles larger knowledge bases, choosing the right “data language” becomes as critical as the reasoning logic itself. Paper: [KG-LLM-Bench: A Scalable Benchmark for Evaluating LLM Reasoning on Textualized Knowledge Graphs] Authors: Elan Markowitz, Krupa Galiya, Greg Ver Steeg, Aram Galstyan

🚀 Thrilled to share our latest work published in Nature Machine Intelligence! 📄 "A comprehensive large-scale biomedical knowledge graph for AI-powered data-driven biomedical research" In this study, we constructed iKraph, one of the most comprehensive biomedical knowledge graphs to date, using a human-level information extraction pipeline that won both the LitCoin NLP Challenge and the BioCreative Challenge. iKraph integrates insights from over 34 million PubMed abstracts and 40 public databases, enabling unprecedented scale and precision in automated knowledge discovery (AKD). 💡 What sets our work apart? We developed a causal knowledge graph and a probabilistic semantic reasoning (PSR) algorithm to infer indirect entity relationships, such as drug-disease relationships. This time-aware framework allowed us to retrospectively and prospectively validate drug repurposing and drug target predictions, something rarely done in prior work. ✅ For COVID-19, we predicted hundreds of drug candidates in real-time, one-third of which were later supported by clinical trials or publications. ✅ For cystic fibrosis, we demonstrated our predictions were often validated up to a decade later, suggesting our method could significantly accelerate the drug discovery pipeline. ✅ Across diverse diseases and common drugs, we achieved benchmark-setting recall and positive predictive rates, pushing the boundaries of what's possible in drug repurposing. We believe this study sets a new frontier in biomedical discovery and demonstrates the power of structured knowledge and interpretability in real-world applications. 📚 Read the full paper: https://lnkd.in/egYgbYT4? 📌 Access the platform: https://lnkd.in/ecxwHBK7 📂 Access the data and code: https://lnkd.in/eBp2GEnH LitCoin NLP Challenge: https://lnkd.in/e-cBc6eR Kudos to our incredible team and collaborators who made this possible! #DrugDiscovery #AI #KnowledgeGraph #Bioinformatics #MachineLearning #NatureMachineIntelligence #DrugRepurposing #LLM #BiomedicalAI #NLP #COVID19 #Insilicom #NIH #NCI #NSF #ARPA-H | 10 comments on LinkedIn

Structuring legal information as a knowledge graph to increase the answer accuracy using a LangGraph agent

It seems the answer on whether an LMM would be able to replace the whole text-to-ontology pipeline is a resounding ‘no’. If you’re one of those who think that should be (or even is?) a ‘yes’: why, and did you do the experiments that show it’s as good as the alternatives (with the results available)? And I mean a proper ontology, not a knowledge graph with numerous duplications and contradictions and lacking constraints. For a few gentle considerations (and pointers to longer arguments) and a summary figure of processes the LLM supposedly would be replacing: see https://lnkd.in/dG_Xsv_6 | 43 comments on LinkedIn

Learn how to use Spanner Graph with LangChain workflows to build advanced, relationship-aware RAG systems, a.k.a. GraphRAG.

This blog post is part of a series that dives into various aspects of SAP’s approach to Generative AI, and its technical underpinnings. In previous blog posts of this series, you learned about how to use large language models (LLMs) for developing AI applications in a trustworthy and reliable manner...

Read about how our partners from Semantic Partners explore the latest iteration of the GraphDB's Talk To Your Graph feature

Multi-Layer Agentic Reasoning: Connecting Complex Data and Dynamic Insights in Graph-Based RAG Systems 🛜 At the most fundamental level, all approaches rely… | 11 comments on LinkedIn

Build a graph for RAG application for a price of a chocolate bar! What is GraphRAG for you? What is GraphRAG? What does GraphRAG mean from your perspective? What if you could have a standard RAG and a GraphRAG as a combi-package, with just a query switch? The fact is, there is no concrete, universal

🎁⏳ Zep packs Temporal Knowledge Graphs + Semantic Entity Extraction + Cypher Queries storage—Outperforming MemGPT with 94.8% Accuracy. Build Personalized AI… | 46 comments on LinkedIn

Copyright 2025 Kurt Cagle / The Ontologist

To gain competitive advantage from gen AI, enterprises need to be able to add their own expertise to off-the-shelf systems. Yet standard enterprise data stores aren't a good fit to train large language models.

🎉 We're thrilled to unveil Synalinks (🧠🔗), an open-source framework designed to streamline the creation, evaluation, training, and deployment of…

Breaking LLM Hallucinations in a Smarter Way! (It’s not about feeding more data) Large Language Models (LLMs) still struggle with factual inaccuracies, but…

Build a knowledge graph without an LLM for your RAG applications

KET-RAG: Turbocharging AI Agents with 10x Cheaper, Smarter Knowledge Retrieval This Multi-Granular Graph Framework uses PageRank and Keyword-Chunk Graph to have the Best Cost-Quality Tradeoff ﹌﹌﹌﹌﹌﹌﹌﹌﹌ 》The Problem: Knowledge Graphs Are Expensive (and Clunky) AI agents need context to answer complex questions—like connecting “COVID vaccines” to “myocarditis risks” across research papers. But today’s solutions face two nightmares: ✸ Cost: Building detailed knowledge graphs with LLMs can cost $33,000 for a 5GB legal case. ✸ Quality: Cheap methods (like KNN graphs) miss key relationships, leading to 32% worse answers. ☆ Imagine training an AI doctor that either bankrupts you or misdiagnoses patients. Ouch. ﹌﹌﹌﹌﹌﹌﹌﹌﹌ 》The Fix: KET-RAG’s Two-Layer Brain KET-RAG merges precision (knowledge graphs) and efficiency (keyword-text maps) into one system: ✸ Layer 1: Knowledge Graph Skeleton ☆ Uses PageRank to find core text chunks (like “vaccine side effects” in medical docs). ☆ Builds a sparse graph only on these chunks with LLMs—saving 80% of indexing costs. ✸ Layer 2: Keyword-Chunk Bipartite Graph ☆ Links keywords (e.g., “myocarditis”) to all related text snippets—no LLM needed. ☆ Acts as a “fast lane” for retrieving context without expensive entity extraction. ﹌﹌﹌﹌﹌﹌﹌﹌﹌ 》Results: Beating Microsoft’s Graph-RAG with Pennies On HotpotQA and MuSiQue benchmarks, KET-RAG: ✸ Retrieves 81.6% of critical info vs. Microsoft’s 74.6%—with 10x lower cost. ✸ Boosts answer accuracy (F1 score) by 32.4% while cutting indexing bills by 20%. ✸ Scales to terabytes of data without melting budgets. ☆ Think of it as a Tesla Model 3 outperforming a Lamborghini at 1/10th the price. ﹌﹌﹌﹌﹌﹌﹌﹌﹌ 》Why AI Agents Need This AI agents aren’t just chatbots—they’re problem solvers for medicine, law, and customer service. KET-RAG gives them: ✸ Real-time, multi-hop reasoning: Connecting “drug A → gene B → side effect C” in milliseconds. ✸ Cost-effective scalability: Deploying agents across millions of documents without going broke. ✸ Adaptability: Mixing precise knowledge graphs (for critical data) with keyword maps (for speed). Paper in comments ≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣ 》Build Your Own Supercharged AI Agent? 🔮 Join My 𝐇𝐚𝐧𝐝𝐬-𝐎𝐧 𝐀𝐈 𝐀𝐠𝐞𝐧𝐭𝐬 𝐓𝐫𝐚𝐢𝐧𝐢𝐧𝐠 TODAY! and Learn Building AI Agent with Langgraph/Langchain, CrewAI and OpenAI Swarm + RAG Pipelines 𝐄𝐧𝐫𝐨𝐥𝐥 𝐍𝐎𝐖 [34% discount]: 👉 https://lnkd.in/eGuWr4CH | 10 comments on LinkedIn

Bridge the gap and unlock hidden potential within your unstructured data

New features include community summaries, local and global retrievers, running retrievers in parallel, and custom prompt instructions.

LLMs that automatically fill knowledge gaps - too good to be true? Large Language Models (LLMs) often stumble in logical tasks due to hallucinations, especially when relying on incomplete Knowledge Graphs (KGs). Current methods naively trust KGs as exhaustive truth sources - a flawed assumption in real-world domains like healthcare or finance where gaps persist. SymAgent is a new framework that approaches this problem by making KGs active collaborators, not passive databases. Its dual-module design combines symbolic logic with neural flexibility: 1. Agent-Planner extracts implicit rules from KGs (e.g., "If drug X interacts with Y, avoid co-prescription") to decompose complex questions into structured steps. 2. Agent-Executor dynamically pulls external data when KG triples are missing, bypassing the "static repository" limitation. Perhaps most impressively, SymAgent’s self-learning observes failed reasoning paths to iteratively refine its strategy and flag missing KG connections - achieving 20-30% accuracy gains over raw LLMs. Equipped with SymAgent, even 7B models rival their much larger counterparts by leveraging this closed-loop system. It would be great if LLMs were able to autonomously curate knowledge and adapt to domain shifts without costly retraining. But are we there yet? Are hybrid architectures like SymAgent the future? ↓ Liked this post? Join my newsletter with 50k+ readers that breaks down all you need to know about the latest LLM research: llmwatch.com 💡

When (not) to use GraphRAG

🌟 Pathway to Artificial General Intelligence (AGI) 🌟 This is my view on the evolutionary steps toward AGI: 1️⃣ Large Language Models (LLMs): Language models…

Explore its functionality and how it leverages the power of LLMs and Neo4j graph databases to improve data analysis and knowledge discovery.

The recently developed retrieval-augmented generation (RAG) technology has enabled the efficient construction of domain-specific applications. However, it also has limitations, including the gap...

David Hughes presented “Unleashing the Power of Multimodal GraphRAG: Integrating Image Features for Deeper Insights” at Data Day Texas 2025.