Knowledge Graphs and LLMs in Action
summary
Claims that pairing knowledge graphs with LLMs creates an intelligent advisor that turns scattered structured and unstructured sources into a single machine‑readable graph, uses LLM extraction to graph queries, and supplies verifiable provenance to reduce hallucination. Demonstration centers on a missing‑child case where graph plus LLM entity extraction, camera plate linking and query automation would change a real outcome from 18 years → 18 hours? and a built prototype reports that matchmaking of suspects works pretty well.
AI-written summary · about
chapters (8)
- 0:00Knowledge graphs and LLMs intro
- 5:26Limitations of generative AI
- 7:58Why graphs complement LLMs
- 10:49Case study: Jaycee Dugard
- 14:22Building the knowledge graph
- 18:17Querying with natural language
- 20:45Cross-domain applications
- 21:06Implementation steps
related talks
41mEnhancing LLMs with Graph Technology
44mGive Your LLMs a Left Brain
46mKnowledge Graphs + LLMs: What's the latest in research?
28mEnhancing LLMs with Graph Technology
28mGrounded Intelligence Boosting LLMs with Real-Time Graph Context
20mPractical GraphRAG: Making LLMs smarter with Knowledge Graphs
32mMulti-Agent Query Generation w/ LLMs on Complex Knowledge Graphs
52mGive Your LLMs a Left Brain