An LLM-aided Enterprise Knowledge Graph (EKG) engineering process
Loading...
Author (Corporation)
Publication date
2024
Typ of student thesis
Course of study
Collections
Type
04B - Conference paper
Editors
Editor (Corporation)
Supervisor
Parent work
Proceedings of the AAAI 2024 Spring Symposium Series
Special issue
DOI of the original publication
Link
Series
Series number
Volume
3(1)
Issue / Number
Pages / Duration
148-156
Patent number
Publisher / Publishing institution
Stanford University
Place of publication / Event location
Stanford
Edition
Version
Programming language
Assignee
Practice partner / Client
Abstract
Conventional knowledge engineering approaches aiming to create Enterprise Knowledge Graphs (EKG) still require a high level of manual effort and high ontology expertise, which hinder their adoption across industries. To tackle this issue, we explored the use of Large Language Models (LLMs) for the creation of EKGs through the lens of a design-science approach. Findings from the literature and from expert interviews led to the creation of the proposed artefact, which takes the form of a six-step process for EKG development. Scenarios on how to use LLMs are proposed and implemented for each of the six steps. The process is then evaluated with an anonymised data set from a large Swiss company. Results demonstrate that LLMs can support the creation of EKGs, offering themselves as a new aid for knowledge engineers.
Keywords
Subject (DDC)
Event
AAAI-MAKE
Exhibition start date
Exhibition end date
Conference start date
Conference end date
Date of the last check
ISBN
978-1-57735-894-7
ISSN
Language
English
Created during FHNW affiliation
Yes
Strategic action fields FHNW
Publication status
Published
Review
Peer review of the complete publication
Open access category
Closed
License
Citation
Laurenzi, E., Mathys, A., & Martin, A. (2024). An LLM-aided Enterprise Knowledge Graph (EKG) engineering process. In R. Petrick & C. Geib (Eds.), Proceedings of the AAAI 2024 Spring Symposium Series: Vol. 3(1) (pp. 148–156). Stanford University. https://doi.org/10.1609/aaaiss.v3i1.31194