Simulations vs Models
We often refer to generative AI systems as models, but would it be more accurate to call them simulations?
Models aim to capture the essence of a system, preserving its logic and structure in a way that enables reasoning, prediction, and deeper understanding. A simulation, on the other hand, mimics the observable behaviour of a system without necessarily representing its underlying structure or logic. While both are valuable, they serve different purposes: models aim to explain and understand, whereas simulations focus on reproducing and predicting.
🔵 LLMs: Curve Fitting Simulations
Large Language Models are fundamentally statistical systems, designed to predict and generate text based on patterns observed in vast training datasets. At their core, LLMs are curve-fitting mechanisms, optimising billions of parameters to minimise prediction error. They model statistical correlations, which excel at generating plausible text but ultimately seem to fall short of formal understanding.
🔵 KGs: Ontologically Committed Models
Knowledge Graphs' defining characteristic is their "ontological commitment". They are grounded in formal ontologies that specify concepts, categories, and relationships, enabling a shared understanding of the data. For instance, "employee" in a Knowledge Graph is not merely a token but a defined entity with explicit relationships to concepts like "employer," "role," or "contract." This formalisation supports reasoning and inference, allowing Knowledge Graphs to serve as "computable frameworks for understanding" but this is not quite actual understanding either.
🔵 Semantic Agents
The distinction between LLMs and KGs is foundational to how we approach the development of AI Agents.
🔹 LLMs excel in tasks prioritising fluency, flexibility, and general common knowledge. They can creatively explore the data presented to them, building on a foundation of prior knowledge compressed from vast, web-based training datasets.
🔹 Knowledge Graphs provide a structured, formalised foundation for representing and reasoning about complex systems. They enable explicit domain modelling, promote data interoperability, and support consistent, reliable reasoning. In doing so, they can encapsulate the unique identity and proprietary data of a given organisation, offering a formal representation of the organisation's "world model."
By understanding these differences, we can better align tools to their respective strengths. The future does not lie in choosing one over the other but in exploring how LLMs and Knowledge Graphs can complement each other. Together, they can function in a "Neural-Symbolic Loop," harnessing the generative strengths of LLMs alongside the structured, reasoning capabilities of Knowledge Graphs. This synergy paves the way for more robust, flexible, and semantically grounded AI Agents: Semantic Agents!
