Knowledge Graphs (KG) provide us with a structured, flexible, transparent, cross-system, and collaborative way of organizing our knowledge and data across various domains in society and industrial as well as scientific disciplines. KGs surpass any other form of representation in terms of effectiveness. However, Knowledge Graph Engineering (KGE) requires in-depth experiences of graph structures, web technologies, existing models and vocabularies, rule sets, logic, as well as best practices. It also demands a significant amount of work. Considering the advancements in large language models (LLMs) and their interfaces and applications in recent years, we have conducted comprehensive experiments with ChatGPT to explore its potential in supporting KGE. In this paper, we present a selection of these experiments and their results to demonstrate how ChatGPT can assist us in the development and management of KGs.
%0 Journal Article
%1 Meyer2023LLMassistedKnowledge
%A Meyer, Lars-Peter
%A Stadler, Claus
%A Frey, Johannes
%A Radtke, Norman
%A Junghanns, Kurt
%A Meissner, Roy
%A Dziwis, Gordian
%A Bulert, Kirill
%A Martin, Michael
%D 2023
%K es frey group_aksw junghanns lpmeyer martin meissner radtke stadler
%R 10.48550/ARXIV.2307.06917
%T LLM-assisted Knowledge Graph Engineering: Experiments with ChatGPT
%X Knowledge Graphs (KG) provide us with a structured, flexible, transparent, cross-system, and collaborative way of organizing our knowledge and data across various domains in society and industrial as well as scientific disciplines. KGs surpass any other form of representation in terms of effectiveness. However, Knowledge Graph Engineering (KGE) requires in-depth experiences of graph structures, web technologies, existing models and vocabularies, rule sets, logic, as well as best practices. It also demands a significant amount of work. Considering the advancements in large language models (LLMs) and their interfaces and applications in recent years, we have conducted comprehensive experiments with ChatGPT to explore its potential in supporting KGE. In this paper, we present a selection of these experiments and their results to demonstrate how ChatGPT can assist us in the development and management of KGs.
@article{Meyer2023LLMassistedKnowledge,
abstract = {Knowledge Graphs (KG) provide us with a structured, flexible, transparent, cross-system, and collaborative way of organizing our knowledge and data across various domains in society and industrial as well as scientific disciplines. KGs surpass any other form of representation in terms of effectiveness. However, Knowledge Graph Engineering (KGE) requires in-depth experiences of graph structures, web technologies, existing models and vocabularies, rule sets, logic, as well as best practices. It also demands a significant amount of work. Considering the advancements in large language models (LLMs) and their interfaces and applications in recent years, we have conducted comprehensive experiments with ChatGPT to explore its potential in supporting KGE. In this paper, we present a selection of these experiments and their results to demonstrate how ChatGPT can assist us in the development and management of KGs.},
added-at = {2024-06-18T09:46:35.000+0200},
author = {Meyer, Lars-Peter and Stadler, Claus and Frey, Johannes and Radtke, Norman and Junghanns, Kurt and Meissner, Roy and Dziwis, Gordian and Bulert, Kirill and Martin, Michael},
biburl = {https://www.bibsonomy.org/bibtex/211a6c76450c9ceb9c3bdedb271a0e849/aksw},
comment = {to appear in proceedings of AI Tomorrow 2023
Results: https://github.com/AKSW/AI-Tomorrow-2023-KG-ChatGPT-Experiments},
doi = {10.48550/ARXIV.2307.06917},
interhash = {34182d80db957a2c81e79aaa374a6e62},
intrahash = {11a6c76450c9ceb9c3bdedb271a0e849},
keywords = {es frey group_aksw junghanns lpmeyer martin meissner radtke stadler},
timestamp = {2024-06-18T09:46:35.000+0200},
title = {LLM-assisted Knowledge Graph Engineering: Experiments with ChatGPT},
year = 2023
}