#artificialintelligence #118: Of Knowledge Graphs and LLMs in Scientific Research and Learning

Ajit Jaokar

Published Jul 16, 2023

Synopsis

In this post, I explain about how we are implementing knowledge graphs and LLMs in Scientific research and learning. This forms a part of my teaching at the #universityofoxford but also a part of #salooki and the #erdos institute.

We are essentially looking at LLMs to accelerate the creation of knowledge graphs especially considering that given a body of knowledge , we can create multiple ontologies of the same subject using LLMs.

For example:

consider a domain like smart cities

That could have multiple ontologies

City Ontology: An ontology representing urban infrastructure, services, and governance.

Energy Ontology: An ontology representing energy-related concepts and relationships.

Etc

Each of these could be created using LLMs.

By combining these ontologies, in a single knowledge graph, a holistic understanding of smart cities can be achieved, encompassing aspects of urban planning, energy management, and transportation systems.

Once created, they can be used in research, applications, learning etc. I am particularly interested in using these ideas to solve hard and complex scientific problems spanning interdisciplinary domains.

Introduction to knowledge graphs and Ontologies

Within the realm of knowledge representation, Knowledge graphs and ontologies are closely related but serve different purposes.

Ontologies, are formal representations of knowledge that define concepts, relationships, and properties within a specific domain. They provide a shared vocabulary and understanding of the entities and their relationships in a particular knowledge domain. Ontologies focus on establishing a structured, hierarchical classification of concepts and defining the relationships and constraints that govern those concepts. For an Environmental Ontology i.e. an ontology for representing environmental concepts, example Classes could be Ecosystem, Species, Habitat, Pollutant etc and example Properties could be inhabits, affects, isPollutedBy. Specific domains have ontologies for ex Gene Ontology

A knowledge graph is a structured representation of knowledge that captures entities, relationships, and attributes in a graph-like structure. It models real-world entities and their interconnections, allowing for rich and flexible data representation. Knowledge graphs are often created by integrating data from various sources and can be dynamically updated as new information becomes available. They emphasize the organization and interlinking of data to create a comprehensive knowledge base.

LLMs and knowledge Graphs

There are essentially two ways in which you can use LLMs and knowledge graphs

Use the LLM to build a KG and
Use the LLM as a natural language interface to the KG

You can use the LLM at each stage of the KG: Identify the relevant entities; Explore entity relationships and attributes; Extract question patterns; Generate questions; Incorporate context and user input; Fill in Placeholder Values; Incorporate Context and Diversity.

LLM-assisted Knowledge Graph Engineering: Experiments with ChatGPT is a good reference. Also see Peter Lawrence blog where an LLM is used to generate a graph based on a specified and supplied ontology.

Applications to Research and Learning

By accelerating the creation of knowledge graphs, we can impact a number of areas in research, science, learning, complex problem solving via creative thinking especially in interdisciplinary areas.

Multiple ontologies can create multiple perspectives as discussed before
We can use knowledge graphs for reasoning. This includes causal reasoning; deductive Reasoning based on logical rules; Semantic Reasoning; Contextual Reasoning; Ontological Reasoning and abductive Reasoning i.e. inferring the best explanation or hypothesis for a given set of observations or facts.
Bloom's Taxonomy and ontologies. Bloom's Taxonomy (see our work here in education) is a hierarchical framework used in education to classify and categorize different levels of cognitive learning. While Bloom's Taxonomy focuses on classifying cognitive skills, ontologies can be used to organize and categorize knowledge itself. Ontologies can support the implementation and application of Bloom's Taxonomy by providing a structured framework for representing knowledge at different levels of complexity.For instance, an ontology might represent concepts and relationships at different levels of Bloom's Taxonomy. It could include basic concepts for remembering and understanding, more complex concepts for applying and analyzing, and higher-level concepts for evaluating and creating.
Ontologies play a crucial role in interdisciplinary research by providing a shared vocabulary and structured representation of knowledge that facilitates communication, collaboration, and integration of different disciplines. Areas of focus include conceptual Integration;Cross-Disciplinary Hypothesis Generation and Reasoning and Education and Training. These could apply in domains such as Drug Discovery and Development; Protein Folding and Structure Prediction; Bioinformatics and Genomics; Climate Modeling and Environmental Science; Material Science and Nanotechnology.

Conclusion

I am working on the following areas:

Looking at LLMs to accelerate the creation of knowledge graphs
This enables us to achieve the following: given a body of knowledge we can create multiple ontologies of the same subject using LLMs.
By accelerating the creation of knowledge graphs, we can impact a number of areas in research, science, learning, complex problem solving via creative thinking especially in interdisciplinary areas.

Please sign up here if you want to stay in touch as we launch

https://lnkd.in/e6yxF5rd

If you want to study with me please sign up for this Artificial Intelligence course at the University of Oxford - (it will be revamped soon and relaunched)

Image source wikipedia knowledge graph