A new article that I co-authored. It explores the benefits of using Knowledge Graphs and LLMs to combat fraud in the welfare state.
"""Fraud detection can be revolutionized with hybrid AI. Combining the “intuitive hunches” from LLMs with a fraud-focused knowledge graph, a multi-agent system can identify weak signals and evolving fraud patterns, moving from detection to prevention in real-time. The challenge? Rule sets need to be cast in iron, whereas the system itself must be like water: resilient and adaptive. Historically, this conflict has been unsolvable. But that is about to change."""
Link to the article: Mulder and Scully for fraud prevention: Teaming up AI capabilities - Capgemini