Saved in:
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.00699 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918317432766464 |
|---|---|
| author | Liu, Xuan Li, Ziyu He, Mu Ma, Ziyang Wu, Xiaoxu Yilmaz, Gizem Xia, Yiyuan Li, Bingbing Tan, He Fuh, Jerry Ying Hsi Lu, Wen Feng Jarfors, Anders E. W. Jansson, Per |
| author_facet | Liu, Xuan Li, Ziyu He, Mu Ma, Ziyang Wu, Xiaoxu Yilmaz, Gizem Xia, Yiyuan Li, Bingbing Tan, He Fuh, Jerry Ying Hsi Lu, Wen Feng Jarfors, Anders E. W. Jansson, Per |
| contents | Ontologies are essential for structuring domain knowledge, improving accessibility, sharing, and reuse. However, traditional ontology construction relies on manual annotation and conventional natural language processing (NLP) techniques, making the process labour-intensive and costly, especially in specialised fields like casting manufacturing. The rise of Large Language Models (LLMs) offers new possibilities for automating knowledge extraction. This study investigates three LLM-based approaches, including pre-trained LLM-driven method, in-context learning (ICL) method and fine-tuning method to extract terms and relations from domain-specific texts using limited data. We compare their performances and use the best-performing method to build a casting ontology that validated by domian expert. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_00699 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | From Prompt to Graph: Comparing LLM-Based Information Extraction Strategies in Domain-Specific Ontology Development Liu, Xuan Li, Ziyu He, Mu Ma, Ziyang Wu, Xiaoxu Yilmaz, Gizem Xia, Yiyuan Li, Bingbing Tan, He Fuh, Jerry Ying Hsi Lu, Wen Feng Jarfors, Anders E. W. Jansson, Per Artificial Intelligence Computation and Language Information Retrieval 68T50, 68T30 J.6; I.2 Ontologies are essential for structuring domain knowledge, improving accessibility, sharing, and reuse. However, traditional ontology construction relies on manual annotation and conventional natural language processing (NLP) techniques, making the process labour-intensive and costly, especially in specialised fields like casting manufacturing. The rise of Large Language Models (LLMs) offers new possibilities for automating knowledge extraction. This study investigates three LLM-based approaches, including pre-trained LLM-driven method, in-context learning (ICL) method and fine-tuning method to extract terms and relations from domain-specific texts using limited data. We compare their performances and use the best-performing method to build a casting ontology that validated by domian expert. |
| title | From Prompt to Graph: Comparing LLM-Based Information Extraction Strategies in Domain-Specific Ontology Development |
| topic | Artificial Intelligence Computation and Language Information Retrieval 68T50, 68T30 J.6; I.2 |
| url | https://arxiv.org/abs/2602.00699 |