Back to Essays

Large Language Models and Knowledge Graphs: A Journey Towards Collaborative Intelligence

A lot has been written about Generative AI (GenAI) powered by transformer based large language models (LLM). OpenAI in sync with Microsoft clearly leads the table with Google and other big players and a bunch of innovative open source options in the fray.

As with any other technology with potential for disruption in varied fields and diverse candidate use cases, attendant hype is in step, causing a lot of confusion.

In the late 1980s, as a young enthusiast working with Expert Systems, I was captivated by the promise of rules-based symbolic AI. I witnessed firsthand the power of these systems and the transformative potential they held. Yet, a challenge remained — it was impossible to manually capture all the nuanced knowledge of human experts into these systems.

Fig 1.0: The Expert System Bottleneck (1989)

Rule Definition: “Chair

Try to define a chair with logic rules.

Complexity Score
10%
1.If object has 4 Legs AND has a seat AND has a back THEN it is a chair
Fig 2.0: The Semantic Trap
Refund Accepted
Refund Denied
Shipping Delay
Product Defect
Return Process
Fig 3.0: The Virtuous Cycle
Truth
Grounded
Unstructured Data
LLM Extraction
KG Validation
Deterministic Answer
System State: Ingesting PDFs...
About the Author
Dilip Ittyera

Dilip Ittyera

CEO and Founder, CogniSwitch·Harvard Business Case Study

4X founder with 35+ years building enterprise knowledge systems. Former CTO at Zensar, NIIT Technologies, and Hexaware. His work on organizational transformation was featured as a Harvard Business School case study. At CogniSwitch, he's focused on making AI reliable enough for regulated industries.