archive – Allessandro Negro
summary
Claims that combining knowledge graph + LLM produces a verifiable, contextual advisor for time‑critical cases, using traffic camera feeds, car registries, parole reports and witness statements; cites a missing‑child case with 60 visits by officers and an 18‑year delay and stresses the 24–48 hour window. Describes an intelligent advisor system that converts natural questions into graph queries, returns candidate images and summarized reports, and in demos “works pretty well” to reduce search time and limit hallucinations.
AI-written summary · about
chapters (8)
- 0:00Introduction
- 1:05Investigative challenges today
- 5:26Generative AI limitations
- 6:53Knowledge graphs and AI tools
- 9:45Intelligent advisor system
- 14:02Jaycee Dugard case with AI
- 20:45Next steps for knowledge graphs
- 22:56Q&A
related talks
28mEnhancing LLMs with Graph Technology
41mEnhancing LLMs with Graph Technology
28mGrounded Intelligence Boosting LLMs with Real-Time Graph Context
32mMulti-Agent Query Generation w/ LLMs on Complex Knowledge Graphs
36mAgentic GraphRAG: AI’s Logical Edge
38mLeveraging Knowledge Graphs for RAG: A Smarter Approach to Contextual AI Applications
25mEnhance LLM Applications' Trustworthiness and Explainability
19mKnowledge Graphs in Litigation Agents