Generating Knowledge Graphs from Large Language Models: A Comparative Study of GPT-4, LLaMA 2, and BERT
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912150691250176 |
|---|---|
| author | Bhatt, Ahan Vaghela, Nandan Dudhia, Kush |
| author_facet | Bhatt, Ahan Vaghela, Nandan Dudhia, Kush |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_07412 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Generating Knowledge Graphs from Large Language Models: A Comparative Study of GPT-4, LLaMA 2, and BERT Bhatt, Ahan Vaghela, Nandan Dudhia, Kush Computation and Language Artificial Intelligence Databases 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. |
| title | Generating Knowledge Graphs from Large Language Models: A Comparative Study of GPT-4, LLaMA 2, and BERT |
| topic | Computation and Language Artificial Intelligence Databases |
| url | https://arxiv.org/abs/2412.07412 |