Accenture AI Leaders Podcast AI Leaders Podcast #69: Knowledge Graphs in the Age of Gen AI
24 snips
Feb 17, 2025 Tony Romito, Technology Consulting Director at Accenture, and Navin Sharma, Head of Product at Stardog, dive into the intriguing world of knowledge graphs. They explain how these tools enhance data management and reasoning, particularly in the age of generative AI. Discover how knowledge graphs tackle issues like hallucinations in language models, their role in enterprise architecture, and their importance in decision-making across industries. The conversation also debunks myths surrounding knowledge graphs, showcasing their continued relevance and value.
AI Snips
Chapters
Transcript
Episode notes
Knowledge Graphs Enhance LLM Accuracy
- Large language models (LLMs) hallucinate because they use statistics, lacking semantic understanding.
- Knowledge graphs add context, improving LLM accuracy by connecting related information and concepts.
Improving LLM Accuracy with Knowledge Graphs
- Use LLMs to generate structured queries, but get answers from trusted sources.
- This ensures traceability and reduces reliance on LLMs for final answers, minimizing hallucinations.
Knowledge Graphs in Biopharma
- A biopharma company used knowledge graphs to connect data from various labs and instruments.
- This enabled better experiment design, testing processes, and analysis of over 7,000 compounds.