Integrating Large Language Models (LLMs) with Knowledge Graphs (KGs) results in complex systems with numerous hyperparameters that directly affect performance. While such systems are increasingly...

Want to Fix LLM Hallucination? Neurosymbolic Alone Won’t Cut It The Conversation’s new piece makes a clear case for neurosymbolic AI—integrating symbolic logic with statistical learning—as the long-term fix for LLM hallucinations. It’s a timely and necessary argument: “No matter how large a language model gets, it can’t escape its fundamental lack of grounding in rules, logic, or real-world structure. Hallucination isn’t a bug, it’s the default.” But what’s crucial—and often glossed over—is that symbolic logic alone isn’t enough. The real leap comes from adding formal ontologies and semantic constraints that make meaning machine-computable. OWL, Shapes Constraint Language (SHACL), and frameworks like BFO, Descriptive Ontology for Linguistic and Cognitive Engineering (DOLCE), the Suggested Upper Merged Ontology (SUMO), and the Common Core Ontologies (CCO) don’t just “represent rules”—they define what exists, what can relate, and under what conditions inference is valid. That’s the difference between “decorating” a knowledge graph and engineering one that can detect, explain, and prevent hallucinations in practice. I’d go further: • Most enterprise LLM hallucinations are just semantic errors—mislabeling, misattribution, or class confusion that only formal ontologies can prevent. • Neurosymbolic systems only deliver if their symbolic half is grounded in ontological reality, not just handcrafted rules or taxonomies. The upshot: We need to move beyond mere integration of symbols and neurons. We need semantic scaffolding—ontologies as infrastructure—to ensure AI isn’t just fluent, but actually right. Curious if others are layering formal ontologies (BFO, DOLCE, SUMO) into their AI stacks yet? Or are we still hoping that more compute and prompt engineering will do the trick? #NeuroSymbolicAI #SemanticAI #Ontology #LLMs #AIHallucination #KnowledgeGraphs #AITrust #AIReasoning

AutoSchemaKG: Building Billion-Node Knowledge Graphs Without Human Schemas 👉 Why This Matters Traditional knowledge graphs face a paradox: they require expert-crafted schemas to organize information, creating bottlenecks for scalability and adaptability. This limits their ability to handle dynamic real-world knowledge or cross-domain applications effectively. 👉 What Changed AutoSchemaKG eliminates manual schema design through three innovations: 1. Dynamic schema induction: LLMs automatically create conceptual hierarchies while extracting entities/events 2. Event-aware modeling: Captures temporal relationships and procedural knowledge missed by entity-only approaches 3. Multi-level conceptualization: Organizes instances into semantic categories through abstraction layers The system processed 50M+ documents to build ATLAS - a family of KGs with: - 900M+ nodes (entities/events/concepts) - 5.9B+ relationships - 95% alignment with human-created schemas (zero manual intervention) 👉 How It Works 1. Triple extraction pipeline:   - LLMs identify entity-entity, entity-event, and event-event relationships   - Processes text at document level rather than sentence level for context preservation 2. Schema induction:   - Automatically groups instances into conceptual categories   - Creates hierarchical relationships between specific facts and abstract concepts 3. Scale optimization:   - Handles web-scale corpora through GPU-accelerated batch processing   - Maintains semantic consistency across 3 distinct domains (Wikipedia, academic papers, Common Crawl) 👉 Proven Impact - Boosts multi-hop QA accuracy by 12-18% over state-of-the-art baselines - Improves LLM factuality by up to 9% on specialized domains like medicine and law - Enables complex reasoning through conceptual bridges between disparate facts 👉 Key Insight The research demonstrates that billion-scale KGs with dynamic schemas can effectively complement parametric knowledge in LLMs when they reach critical mass (1B+ facts). This challenges the assumption that retrieval augmentation needs domain-specific tuning to be effective. Question for Discussion As autonomous KG construction becomes viable, how should we rethink the role of human expertise in knowledge representation? Should curation shift from schema design to validation and ethical oversight? | 15 comments on LinkedIn

Small Models, Big Knowledge: How DRAG Bridges the AI Efficiency-Accuracy Gap 👉 Why This Matters Modern AI systems face a critical tension: large language models (LLMs) deliver impressive knowledge recall but demand massive computational resources, while smaller models (SLMs) struggle with factual accuracy and "hallucinations." Traditional retrieval-augmented generation (RAG) systems amplify this problem by requiring constant updates to vast knowledge bases. 👉 The Innovation DRAG introduces a novel distillation framework that transfers RAG capabilities from LLMs to SLMs through two key mechanisms: 1. Evidence-based distillation: Filters and ranks factual snippets from teacher LLMs 2. Graph-based structuring: Converts retrieved knowledge into relational graphs to preserve critical connections This dual approach reduces model size requirements by 10-100x while improving factual accuracy by up to 27.7% compared to prior methods like MiniRAG. 👉 How It Works 1. Evidence generation: A large teacher LLM produces multiple context-relevant facts 2. Semantic filtering: Combines cosine similarity and LLM scoring to retain top evidence 3. Knowledge graph creation: Extracts entity relationships to form structured context 4. Distilled inference: SLMs generate answers using both filtered text and graph data The process mimics how humans combine raw information with conceptual understanding, enabling smaller models to "think" like their larger counterparts without the computational overhead. 👉 Privacy Bonus DRAG adds a privacy layer by: - Local query sanitization before cloud processing - Returning only de-identified knowledge graphs Tests show 95.7% reduction in potential personal data leakage while maintaining answer quality. 👉 Why It’s Significant This work addresses three critical challenges simultaneously: - Makes advanced RAG capabilities accessible on edge devices - Reduces hallucination rates through structured knowledge grounding - Preserves user privacy in cloud-based AI interactions The GitHub repository provides full implementation details, enabling immediate application in domains like healthcare diagnostics, legal analysis, and educational tools where accuracy and efficiency are non-negotiable.

Your agents, multi-agent systems and LMs apps are still failing with basic logic? We got you covered. Today we're excited to announce Synalinks 0.3 our Keras-based neuro-symbolic framework that bridges the gap between neural networks and symbolic reasoning. Our latest release focuses entirely on the Knowledge Graph layer, delivering production-ready solutions for real-world applications: - Fully constrained KG extraction powered by Pydantic: ensuring that relations connect to the correct entity types. - Seamless integration with our Agents/Chain-of-Thought and Self-Critique modules. - Automatic entity alignment with HSWN. - KG extraction and retrieval optimizable with OPRO and RandomFewShot algorithms. - 100% reliable Cypher query generation through logic-enhanced hybrid triplet retrieval (works with local models too!). - We took extra care to avoid Cypher injection vulnerabilities (yes, we're looking at you, LangGraph 👀) - The retriever don't need the graph schema, as it is included in the way we constrain the generation, avoiding context pollution (hence better accuracy). - We also fixed Synalinks CLI for Windows users along with some minor bug fixes. Our technology combine constrained structured output with in-context reinforcement learning, making enterprise-grade reasoning both highly efficient and cost-effective. Currently supporting Neo4j with plans to expand to other graph databases. Built this initially for a client project, but the results were too good not to share with the community. Want to add support for your preferred graph database? It's just one file to implement! Drop a comment and let's make it happen! #AI #MachineLearning #KnowledgeGraphs #NeuralNetworks #Keras #Neo4j #AIAgents #TechInnovation #OpenSource | 10 comments on LinkedIn

I'm happy to share the draft of the "Semantically Composable Architectures" mini-paper. It is the culmination of approximately four years' work, which began with Coreless Architectures and has now evolved into something much bigger. LLMs are impressive, but a real breakthrough will occur once we surpass the cognitive capabilities of a single human brain. Enabling autonomous large-scale system reverse engineering and large-scale autonomous transformation with minimal to no human involvement, while still making it understandable to humans if they choose to, is a central pillar of making truly groundbreaking changes. We hope the ideas we shared will be beneficial to humanity and advance our civilization further. It is not final and will require some clarification and improvements, but the key concepts are present. Happy to hear your thoughts and feedback. Some of these concepts underpin the design of the Product X system. Part of the core team + external contribution: Andrew Barsukov Andrey Kolodnitsky Sapta Girisa N Keith E. Glendon Gurpreet Sachdeva Saurav Chandra Mike Diachenko Oleh Sinkevych | 13 comments on LinkedIn

The number of published scholarly articles is growing at a significant rate, making scholarly knowledge organization increasingly important. Various approaches have been proposed to organize...

Anthropic is an AI safety and research company that's working to build reliable, interpretable, and steerable AI systems.

Want to explore the Anthropic Transformer-Circuit's as a queryable graph? Wrote a script to import the graph json into Neo4j - code in Gist. https://lnkd.in/eT4NjQgY https://lnkd.in/e38TfQpF Next step - write directly from the circuit-tracer library to the graph db. https://lnkd.in/eVU_t6mS

Introducing FACT: Fast Augmented Context Tools (3.2x faster, 90% cost reduction vs RAG) RAG had its run, but it’s not built for agentic systems. Vectors are fuzzy, slow, and blind to context. They work fine for static data, but once you enter recursive, real-time workflows, where agents need to reason, act, and reflect. RAG collapses under its own ambiguity. That’s why I built FACT: Fast Augmented Context Tools. Traditional Approach: User Query → Database → Processing → Response (2-5 seconds) FACT Approach: User Query → Intelligent Cache → [If Miss] → Optimized Processing → Response (50ms) It replaces vector search in RAG pipelines with a combination of intelligent prompt caching and deterministic tool execution via MCP. Instead of guessing which chunk is relevant, FACT explicitly retrieves structured data, SQL queries, live APIs, internal tools, then intelligently caches the result if it’s useful downstream. The prompt caching isn’t just basic storage. It’s intelligent using the prompt cache from Anthropic and other LLM providers, tuned for feedback-driven loops: static elements get reused, transient ones expire, and the system adapts in real time. Some things you always want cached, schemas, domain prompts. Others, like live data, need freshness. Traditional RAG is particularly bad at this. Ask anyone force to frequently update vector DBs. I'm also using Arcade.dev to handle secure, scalable execution across both local and cloud environments, giving FACT hybrid intelligence for complex pipelines and automatic tool selection. If you're building serious agents, skip the embeddings. RAG is a workaround. FACT is a foundation. It’s cheaper, faster, and designed for how agents actually work: with tools, memory, and intent. To get started point your favorite coding agent at: https://lnkd.in/gek_akem | 38 comments on LinkedIn

🏯🏇 A-MEM Transforms AI Agent Memory with Zettelkasten Method, Atomic Notes, Dynamic Linking & Continuous Evolution! This Novel Memory fixes rigid structures with adaptable, evolving, and interconnected knowledge networks, delivering 2x performance in complex reasoning tasks. 𝗧𝗵𝗶𝘀 𝗶𝘀 𝘄𝗵𝗮𝘁 𝗜 𝗹𝗲𝗮𝗿𝗻𝗲𝗱: ﹌﹌﹌﹌﹌﹌﹌﹌﹌ 》 𝗪𝗵𝘆 𝗧𝗿𝗮𝗱𝗶𝘁𝗶𝗼𝗻𝗮𝗹 𝗠𝗲𝗺𝗼𝗿𝘆 𝗙𝗮𝗹𝗹 𝗦𝗵𝗼𝗿𝘁 Most AI agents today rely on simplistic storage and retrieval but break down when faced with complex, multi-step reasoning tasks. ✸ Common Limitations: ☆ Fixed schemas: Conventional memory systems require predefined structures that limit flexibility. ☆ Limited adaptability: When new information arises, old memories remain static and disconnected, reducing an agent’s ability to build on past experiences. ☆ Ineffective long-term retention: AI agents often struggle to recall relevant past interactions, leading to redundant processing and inefficiencies. ﹌﹌﹌﹌﹌﹌﹌﹌﹌ 》𝗔-𝗠𝗘𝗠: 𝗔𝘁𝗼𝗺𝗶𝗰 𝗻𝗼𝘁𝗲𝘀 𝗮𝗻𝗱 𝗗𝘆𝗻𝗮𝗺𝗶𝗰 𝗹𝗶𝗻𝗸𝗶𝗻𝗴 A-MEM organizes knowledge in a way that mirrors how humans create and refine ideas over time. ✸ How it Works: ☆ Atomic notes: Information is broken down into small, self-contained knowledge units, ensuring clarity and easy integration with future knowledge. ☆ Dynamic linking: Instead of relying on static categories, A-MEM automatically creates connections between related knowledge, forming a network of interrelated ideas. ﹌﹌﹌﹌﹌﹌﹌﹌﹌ 》 𝗣𝗿𝗼𝘃𝗲𝗻 𝗣𝗲𝗿𝗳𝗼𝗿𝗺𝗮𝗻𝗰𝗲 𝗔𝗱𝘃𝗮𝗻𝘁𝗮𝗴𝗲 A-MEM delivers measurable improvements. ✸ Empirical results demonstrate: ☆ Over 2x performance improvement in complex reasoning tasks, where AI must synthesize multiple pieces of information across different timeframes. ☆ Superior efficiency across top foundation models, including GPT, Llama, and Qwen—proving its versatility and broad applicability. ﹌﹌﹌﹌﹌﹌﹌﹌﹌ 》 𝗜𝗻𝘀𝗶𝗱𝗲 𝗔-𝗠𝗘𝗠 ✸ Note Construction: ☆ AI-generated structured notes that capture essential details and contextual insights. ☆ Each memory is assigned metadata, including keywords and summaries, for faster retrieval. ✸ Link Generation: ☆ The system autonomously connects new memories to relevant past knowledge. ☆ Relationships between concepts emerge naturally, allowing AI to recognize patterns over time. ✸ Memory Evolution: ☆ Older memories are continuously updated as new insights emerge. ☆ The system dynamically refines knowledge structures, mimicking the way human memory strengthens connections over time. ≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣ ⫸ꆛ Want to build Real-World AI agents? Join My 𝗛𝗮𝗻𝗱𝘀-𝗼𝗻 𝗔𝗜 𝗔𝗴𝗲𝗻𝘁 𝟰-𝗶𝗻-𝟭 𝗧𝗿𝗮𝗶𝗻𝗶𝗻𝗴 TODAY! 𝟰𝟴𝟬+ already Enrolled. ➠ Build Real-World AI Agents for Healthcare, Finance,Smart Cities,Sales ➠ Learn 4 Framework: LangGraph | PydanticAI | CrewAI | OpenAI Swarm ➠ Work with Text, Audio, Video and Tabular Data 👉𝗘𝗻𝗿𝗼𝗹𝗹 𝗡𝗢𝗪 (𝟰𝟱% 𝗱𝗶𝘀𝗰𝗼𝘂𝗻𝘁): https://lnkd.in/eGuWr4CH | 27 comments on LinkedIn

RAG vs Graph RAG, explained visually. (it's a popular LLM interview question) Imagine you have a long document, say a biography, about an individual (X) who has accomplished several things in this life. ↳ Chapter 1: Talks about Accomplishment-1. ↳ Chapter 2: Talks about Accomplishment-2. ... ↳ Chapter 10: Talks about Accomplishment-10. Summarizing all these accomplishments via RAG might never be possible since... ...it must require the entire context... ...but one might only be fetching the top-k relevant chunks from the vector db. Moreover, since traditional RAG systems retrieve each chunk independently, this can often leave the LLM to infer the connections between them (provided the chunks are retrieved). Graph RAG solves this. The idea is to first create a graph (entities & relationships) from the documents and then do traversal over that graph during the retrieval phase. See how Graph RAG solves the above problems. - First, a system (typically an LLM) will create the graph by understanding the biography. - This will produce a full graph of nodes entities & relationships, and a subgraph will look like this: ↳ X → → Accomplishment-1. ↳ X → → Accomplishment-2. ... ↳ X → → Accomplishment-N. When summarizing these accomplishments, the retrieval phase can do a graph traversal to fetch all the relevant context related to X's accomplishments. This context, when passed to the LLM, will produce a more coherent and complete answer as opposed to traditional RAG. Another reason why Graph RAG systems are so effective is because LLMs are inherently adept at reasoning with structured data. Graph RAG instills that structure into them with their retrieval mechanism. 👉 Over to you: What are some other issues with traditional RAG systems that Graph RAG solves? ____ Find me → Avi Chawla Every day, I share tutorials and insights on DS, ML, LLMs, and RAGs. | 24 comments on LinkedIn

In the age of AI-driven applications, the ability to ground large language models (LLMs) with trustworthy, contextual information is more…

Retrieval-Augmented Generation (RAG) has significantly enhanced large language models (LLMs) in knowledge-intensive tasks by incorporating external knowledge retrieval. However, existing RAG...

Join the discussion on this paper page

Comparative Review of Semantic Knowledge Graph vs Property Knowledge Graph

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

A serious knowledge graph effort is much more than a bit of Github, but customers and adventurous minds keep asking me if there is an easy to use (read: POC click-and-go solution) graph RAG open source stack they can use to generate knowledge graphs. So, here is my list of projects I keep an eye on. Mind, there is nothing simple if you venture into graphs, despite all the claims and marketing. Things like graph machine learning, graph layout and distributed graph analytics is more than a bit of pip install. The best solutions are hidden inside multi-nationals, custom made. Equity firms and investors sometimes ask me to evaluate innovations. It's amazing what talented people develop and never shows up in the news, or on Github. TrustGraph - The Knowledge Platform for AI https://trustgraph.ai/ The only one with a distributed architecture and made for enterprise KG. itext2kg - https://lnkd.in/e-eQbwV5 Clean and plain. Wrapped prompts done right. Fast GraphRAG - https://lnkd.in/e7jZ9GZH Popular and with some basic visualization. ZEP - https://lnkd.in/epxtKtCU Geared towards agentic memory. Triplex - https://lnkd.in/eGV8FR56 LLM to extract triples. GraphRAG Local with UI - https://lnkd.in/ePGeqqQE Another starting point for small KG efforts. Or to convince your investors. GraphRAG visualizer - https://lnkd.in/ePuMmfkR Makes pretty pictures but not for drill-downs. Neo4j's GraphRAG - https://lnkd.in/ex_A52RU A python package with a focus on getting data into Neo4j. OpenSPG - https://lnkd.in/er4qUFJv Has a different take and more academic. Microsoft GraphRAG - https://lnkd.in/e_a-mPum A classic but I don't think anyone is using this beyond experimentation. yWorks - https://www.yworks.com If you are serious about interactive graph layout. Ogma - https://lnkd.in/evwnJCBK If you are serious about graph data viz. Orbifold Consulting - https://lnkd.in/e-Dqg4Zx If you are serious about your KG journey. #GraphRAG #GraphViz #GraphMachineLearning #KnowledgeGraphs

LLMs generate possibilities; knowledge graphs remember what works. Together, they forge the recursive memory and creative engine that enables AI systems to truly evolve themselves. Combining neural components (like large language models) with symbolic verification creates a powerful framework for self-evolution that overcomes limitations of either approach used independently. AlphaEvolve demonstrates that self-evolving systems face a fundamental tension between generating novel solutions and ensuring those solutions actually work. The paper shows how AlphaEvolve addresses this through a hybrid architecture where: Neural components (LLMs) provide creative generation of code modifications by drawing on patterns learned from vast training data Symbolic components (code execution) provide ground truth verification through deterministic evaluation Without this combination, a system would either generate interesting but incorrect solutions (neural-only approach) or be limited to small, safe modifications within known patterns (symbolic-only approach). The system can operate at multiple levels of abstraction depending on the problem: raw solution evolution, constructor function evolution, search algorithm evolution, or co-evolution of intermediate solutions and search algorithms. This capability emanates directly from the neurosymbolic integration, where: Neural networks excel at working with continuous, high-dimensional spaces and recognizing patterns across abstraction levels Symbolic systems provide precise representations of discrete structures and logical relationships This enables AlphaEvolve to modify everything from specific lines of code to entire algorithmic approaches. While AlphaEvolve currently uses an evolutionary database, a knowledge graph structure could significantly enhance self-evolution by: Capturing evolutionary relationships between solutions Identifying patterns of code changes that consistently lead to improvements Representing semantic connections between different solution approaches Supporting transfer learning across problem domains Automated, objective evaluation is the core foundation enabling self-evolution: The main limitation of AlphaEvolve is that it handles problems for which it is possible to devise an automated evaluator. This evaluation component provides the "ground truth" feedback that guides evolution, allowing the system to: Differentiate between successful and unsuccessful modifications Create selection pressure toward better-performing solutions Avoid hallucinations or non-functional solutions that might emerge from neural components alone. When applied to optimize Gemini's training kernels, the system essentially improved the very LLM technology that powers it. | 12 comments on LinkedIn

I added a Knowledge Graph to Cursor using MCP. You gotta see this working! Knowledge graphs are a game-changer for AI Agents, and this is one example of how you can take advantage of them. How this works: 1. Cursor connects to Graphiti's MCP Server. Graphiti is a very popular open-source Knowledge Graph library for AI agents. 2. Graphiti connects to Neo4j running locally. Now, every time I interact with Cursor, the information is synthesized and stored in the knowledge graph. In short, Cursor now "remembers" everything about our project. Huge! Here is the video I recorded. To get this working on your computer, follow the instructions on this link: https://lnkd.in/eeZ_4dkb Something super cool about using Graphiti's MCP server: You can use one model to develop the requirements and a completely different model to implement the code. This is a huge plus because you could use the stronger model at each stage. Also, Graphiti supports custom entities, which you can use when running the MCP server. You can use these custom entities to structure and recall domain-specific information, which will tenfold the accuracy of your results. Here is an example of what these look like: https://lnkd.in/efv7kTaH By the way, knowledge graphs for agents are a big thing. A few ridiculous and eye-opening benchmarks comparing an AI Agent using knowledge graphs with state-of-the-art methods: • 94.8% accuracy versus 93.4% in the Deep Memory Retrieval (DMR) benchmark. • 71.2% accuracy versus 60.2% on conversations simulating real-world enterprise use cases. • 2.58s of latency versus 28.9s. • 38.4% improvement in temporal reasoning. You'll find these benchmarks in this paper: https://fnf.dev/3CLQjBK | 36 comments on LinkedIn

𝙏𝙝𝙤𝙪𝙜𝙝𝙩 𝙛𝙤𝙧 𝙩𝙝𝙚 𝘿𝙖𝙮: What if we could encapsulate everything a person knows—their entire bubble of knowledge, what I’d call a Personal Knowledge Domain or better, our 𝙎𝙚𝙢𝙖𝙣𝙩𝙞𝙘 𝙎𝙚𝙡𝙛, and represent it in an RDF graph? From that foundation, we could create Personal Agents that act on our behalf. Each of us would own our agent, with the ability to share or lease it for collaboration with other agents. If we could make these agents secure, continuously updatable, and interoperable, what kind of power might we unlock for the human race? Is this idea so far-fetched? It has solid grounding in knowledge representation, identity theory, and agent-based systems. It fits right in with current trends: AI assistants, the semantic web, Web3 identity, and digital twins. Yes, the technical and ethical hurdles are significant, but this could become the backbone of a future architecture for personalized AI and cooperative knowledge ecosystems. Pieces of the puzzle already exist: Tim Berners-Lee’s Solid Project, digital twins for individuals, Personal AI platforms like personal.ai, Retrieval-Augmented Language Model agents (ReALM), and Web3 identity efforts such as SpruceID, architectures such as MCP and inter-agent protocols such as A2A. We see movement in human-centric knowledge graphs like FOAF and SIOC, learning analytics, personal learning environments, and LLM-graph hybrids. What we still need is a unified architecture that: * Employs RDF or similar for semantic richness * Ensures user ownership and true portability * Enables secure agent-to-agent collaboration * Supports continuous updates and trust mechanisms * Integrates with LLMs for natural, contextual reasoning These are certainly not novel notions, for example: * MyPDDL (My Personal Digital Life) and the PDS (Personal Data Store) concept from MIT and the EU’s DECODE project. * The Human-Centric AI Group at Stanford and the Augmented Social Cognition group at PARC have also published research around lifelong personal agents and social memory systems. However, one wonders if anyone is working on combining all of the ingredients into a fully baked cake - after which we can enjoy dessert while our personal agents do our bidding. | 21 comments on LinkedIn

Imagine you’re handed a mountain of books in a language you barely speak. Traditional RAG systems do just that: they treat every text…

Perhaps you’ve come across the paper From Local to Global: A GraphRAG Approach to Query-Focused Summarization, which is Microsoft…

The new AI powered Anayltics stack is here…says Gartner’s Afraz Jaffri ! A key element of that stack is an ontology powered Semantic Layer that serves as the brain for AI agents to act on knowledge of your internal data and deliver timely, accurate and hallucination-free insights! #semanticlayer #knowledgegraphs #genai #decisionintelligence

Do you want to fine-tune an LLM model for triplet extraction? These findings from a recently published paper (first comment) could save you much time. ✅ Does the choice of coding vs natural language prompts significantly impact performance? When fine-tuning these open weights and small LLMs, the choice between code and natural language prompts has a limited impact on performance. ✅ Does training fine-tuned models to include chain-of-thought (rationale) sections in their outputs improve KG construction (KGC) performance? It is ineffective at best and highly detrimental at worst for fine-tuned models. This performance decrease is observed regardless of the number of in-context learning examples provided. Attention analysis suggests this might be due to the model's attention being dispersed on redundant information when rationale is used. Without rationale lists occupying prompt space, the model's attention can focus directly on the ICL examples while extracting relations. ✅ How do the fine-tuned smaller, open-weight LLMs perform compared to the CodeKGC baseline, which uses larger, closed-source models (GPT-3.5)? The selected lightweight LLMs significantly outperform the much larger CodeKGC baseline after fine-tuning. The best fine-tuned models improve upon the CodeKGC baseline by as much as 15–20 absolute F1 points across the dataset. ✅ Does model size matter for KGC performance when fine-tuning with a small amount of training data? Yes, but not in a straightforward way. The 70 B-parameter versions yielded worse results than the 1B, 3B, and 8B models when undergoing the same small amount of training. This implies that for KGC with limited fine-tuning, smaller models can perform better than much larger ones. ✅ For instruction-tuned models without fine-tuning, does prompt language or rationale help? For models without fine-tuning, using code prompts generally yields the best results for both code LLMs and the Mistral natural language model. In addition, using rationale generally seems to help these models, with most of the best results obtained when including rationale lists in the prompt. ✅ What do the errors made by the models suggest about the difficulty of the KGC task? difficulty in predicting relations, entities, and their order, especially when dealing with specialized terminology or specific domain knowledge, which poses a challenge even after fine-tuning. Some errors include adding superfluous adjectives or mistaking entity instances for class names. ✅ What is the impact of the number of in-context learning (ICL) examples during fine-tuning? The greatest performance benefit is obtained when moving from 0 to 3 ICL examples. However, additional ICL examples beyond 3 do not lead to any significant performance delta and can even lead to worse results. This further indicates that the fine-tuning process itself is the primary driver of performance gain, allowing the model to learn the task from the input text and target output.

NodeRAG restructures knowledge into a heterograph: a rich, layered, musical graph where each node plays a different role. It’s not just smarter retrieval. It’s structured memory for AI agents. 》 Why NodeRAG? Most Retrieval-Augmented Generation (RAG) methods retrieve chunks of text. Good enough — until you need reasoning, precision, and multi-hop understanding. This is how NodeRAG solves these problems: 》 🔹Step 1: Graph Decomposition NodeRAG begins by decomposing raw text into smart building blocks: ✸ Semantic Units (S): Little event nuggets ("Hinton won the Nobel Prize.") ✸ Entities (N): Key names or concepts ("Hinton", "Nobel Prize") ✸ Relationships (R): Links between entities ("awarded to") ✩ This is like teaching your AI to recognize the actors, actions, and scenes inside any document. 》 🔹Step 2: Graph Augmentation Decomposition alone isn't enough. NodeRAG augments the graph by identifying important hubs: ✸ Node Importance: Using K-Core and Betweenness Centrality to find critical nodes ✩ Important entities get special attention — their attributes are summarized into new nodes (A). ✸ Community Detection: Grouping related nodes into communities and summarizing them into high-level insights (H). ✩ Each community gets a "headline" overview node (O) for quick retrieval. It's like adding context and intuition to raw facts. 》 🔹 Step 3: Graph Enrichment Knowledge without detail is brittle. So NodeRAG enriches the graph: ✸ Original Text: Full chunks are linked back into the graph (Text nodes, T) ✸ Semantic Edges: Using HNSW for fast, meaningful similarity connections ✩ Only smart nodes are embedded (not everything!) — saving huge storage space. ✩ Dual search (exact + vector) makes retrieval laser-sharp. It’s like turning a 2D map into a 3D living world. 》 🔹 Step 4: Graph Searching Now comes the magic. ✸ Dual Search: First find strong entry points (by name or by meaning) ✸ Shallow Personalized PageRank (PPR): Expand carefully from entry points to nearby relevant nodes. ✩ No wandering into irrelevant parts of the graph. The search is surgical. ✩ Retrieval includes fine-grained semantic units, attributes, high-level elements — everything you need, nothing you don't. It’s like sending out agents into a city — and they return not with everything they saw, but exactly what you asked for, summarized and structured. 》 Results: NodeRAG's Performance Compared to GraphRAG, LightRAG, NaiveRAG, and HyDE — NodeRAG wins across every major domain: Tech, Science, Writing, Recreation, and Finance. NodeRAG isn’t just a better graph. NodeRAG is a new operating system for memory. ≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣≣ ⫸ꆛ Want to build Real-World AI agents? Join My 𝗛𝗮𝗻𝗱𝘀-𝗼𝗻 𝗔𝗜 𝗔𝗴𝗲𝗻𝘁 𝗧𝗿𝗮𝗶𝗻𝗶𝗻𝗴 TODAY! ➠ Build Real-World AI Agents + RAG Pipelines ➠ Learn 3 Tools: LangGraph/LangChain | CrewAI | OpenAI Swarm ➠ Work with Text, Audio, Video and Tabular Data 👉𝗘𝗻𝗿𝗼𝗹𝗹 𝗡𝗢𝗪 (𝟯𝟰% 𝗱𝗶𝘀𝗰𝗼𝘂𝗻𝘁): https://lnkd.in/eGuWr4CH | 20 comments on LinkedIn

ServiceNow will acquire AI data quality vendor Data.world in a quest for better management of corporate data for AI.

Today, Amazon Web Services (AWS) announced the general availability of Amazon Bedrock Knowledge Bases GraphRAG (GraphRAG), a capability in Amazon Bedrock Knowledge Bases that enhances Retrieval-Augmented Generation (RAG) with graph data in Amazon Neptune Analytics. In this post, we discuss the benefits of GraphRAG and how to get started with it in Amazon Bedrock Knowledge Bases.