LLM-Supported Formal Knowledge Representation for Enhancing Control Engineering Content with an Interactive Semantic Layer

TL;DR

This paper introduces an LLM-supported semi-automated method for transforming natural language and mathematical descriptions into formal knowledge graphs, enhancing control engineering documentation with an interactive semantic layer.

Contribution

It presents a novel approach combining language models with the PyIRK framework to generate formal, human-readable, and machine-interpretable knowledge representations in control engineering.

Findings

Successful transformation of LaTeX and natural language into formal knowledge graphs

Development of an interactive semantic layer for control engineering documents

Facilitation of knowledge transfer and collaboration in control engineering

Abstract

The rapid growth of research output in control engineering calls for new approaches to structure and formalize domain knowledge. This paper briefly describes an LLM-supported method for semi-automated generation of formal knowledge representations that combine human readability with machine interpretability and increased expressiveness. Based on the Imperative Representation of Knowledge (PyIRK) framework, we demonstrate how language models can assist in transforming natural-language descriptions and mathematical definitions (available as LaTeX source code) into a formalized knowledge graph. As a first application we present the generation of an ``interactive semantic layer'' to enhance the source documents in order to facilitate knowledge transfer. From our perspective this contributes to the vision of easily accessible, collaborative, and verifiable knowledge bases for the control engineering domain.