#knowledge-graphs
Every summary, chronological. Filter by category, tag, or source from the rail.
KNOWPLAN: Knowledge-Driven AI Agents for Degree Planning
KNOWPLAN is an AI agent framework that integrates structured knowledge graphs with LLMs to solve complex academic degree pathway planning, ensuring adherence to institutional constraints and student goals.
Ontology-Guided Extraction for Knowledge Graph Construction
A framework for building knowledge graphs from heterogeneous documents by using ontologies to guide entity extraction and integrating deduplication directly into the extraction layer to ensure data consistency.
SCAIR: Schema-Conditioned Agentic Iterative Reasoning
SCAIR improves enterprise knowledge graph accuracy by using schema-constrained iterative reasoning, preventing LLMs from hallucinating relationships that violate predefined data structures.
Provenance for LLM-Built Knowledge Graphs
LLM synthesis destroys data lineage. By modeling provenance as a graph rather than a flat log, you can trace facts to their sources, enable granular data deletion, and debug agent outputs.
AI EngineerUsing Ontologies as Logical Guardrails for AI Agents
LLMs are probabilistic and prone to errors in complex domains. By wrapping agent loops with formal ontologies (RDFS/OWL) and Pydantic validation, you can enforce strict business logic that natural language prompts cannot guarantee.
DysLexLens: A Framework for Analyzing Dyslexic Learner AI Experiences
DysLexLens is an end-to-end, evidence-traceable framework that uses dictionary-driven filtering and knowledge graphs to analyze how dyslexic learners interact with AI tools via online forums.
Building Context Graphs for AI Agent Decision-Making
Context graphs improve agent accuracy by storing 'decision traces'—the reasoning and historical precedents behind past outcomes—allowing agents to perform structural similarity searches alongside standard semantic retrieval.
AI EngineerBuilding Decision-Aware AI Agents with Context Graphs
Context graphs move AI agents beyond simple knowledge retrieval by embedding policies, rules, and historical precedents, enabling agents to perform explicit risk-value analysis before acting.
AI EngineerFormalizing Agentic Knowledge Graphs for LLM Discoverability
The paper proposes a formal framework for 'Agentic KG Affordances,' enabling AI agents to programmatically discover and interact with knowledge graphs by standardizing how knowledge is exposed and queried.
Beyond RAG: Building Hybrid Knowledge Architectures
RAG is effective for static, unstructured retrieval but fails at reasoning, structured data, and long-term memory. Production systems require hybrid architectures that combine retrieval with knowledge graphs and persistent state.
NLP Progression: Word Clouds to Knowledge Graphs
Build semantic systems from text by progressing: word cloud (frequency) → TF-IDF (importance) → co-occurrence graph (relationships) → knowledge graph (durable meaning). Skip intermediates and your graph stores noise.
Showing 11 of 11