Generating Knowledge Graphs from Large Language Models: A Comparative Study of GPT-4, LLaMA 2, and BERT
Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:6H7WAIZZrecord.jsonopen to challenge →
read the original abstract
Knowledge Graphs (KGs) are essential for the functionality of GraphRAGs, a form of Retrieval-Augmented Generative Systems (RAGs) that excel in tasks requiring structured reasoning and semantic understanding. However, creating KGs for GraphRAGs remains a significant challenge due to accuracy and scalability limitations of traditional methods. This paper introduces a novel approach leveraging large language models (LLMs) like GPT-4, LLaMA 2 (13B), and BERT to generate KGs directly from unstructured data, bypassing traditional pipelines. Using metrics such as Precision, Recall, F1-Score, Graph Edit Distance, and Semantic Similarity, we evaluate the models' ability to generate high-quality KGs. Results demonstrate that GPT-4 achieves superior semantic fidelity and structural accuracy, LLaMA 2 excels in lightweight, domain-specific graphs, and BERT provides insights into challenges in entity-relationship modeling. This study underscores the potential of LLMs to streamline KG creation and enhance GraphRAG accessibility for real-world applications, while setting a foundation for future advancements.
This paper has not been read by Pith yet.
Forward citations
Cited by 2 Pith papers
-
Restructure This: Using AI to Restructure Onboarding Documents to Reduce Cognitive Overload
VisDoc uses GenAI to restructure OSS onboarding documentation according to CTML principles, yielding higher task success and lower cognitive load in a small newcomer study.
-
Restructure This: Using AI to Restructure Onboarding Documents to Reduce Cognitive Overload
VisDoc uses a GenAI pipeline grounded in CTML to restructure OSS onboarding docs, with small evaluations showing higher task success and lower cognitive load.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.