GKG-LLM: A Unified Framework for Generalized Knowledge Graph Construction
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915199688114176 |
|---|---|
| author | Zhang, Jian Wei, Bifan Qi, Shihao Zhu, haiping Liu, Jun Lin, Qika |
| author_facet | Zhang, Jian Wei, Bifan Qi, Shihao Zhu, haiping Liu, Jun Lin, Qika |
| contents | The construction of Generalized Knowledge Graph (GKG), including knowledge graph, event knowledge graph and commonsense knowledge graph, is fundamental for various natural language processing tasks. Current studies typically construct these types of graph separately, overlooking holistic insights and potential unification that could be beneficial in computing resources and usage perspectives. However, a key challenge in developing a unified framework for GKG is obstacles arising from task-specific differences. In this study, we propose a unified framework for constructing generalized knowledge graphs to address this challenge. First, we collect data from 15 sub-tasks in 29 datasets across the three types of graphs, categorizing them into in-sample, counter-task, and out-of-distribution (OOD) data. Then, we propose a three-stage curriculum learning fine-tuning framework, by iteratively injecting knowledge from the three types of graphs into the Large Language Models. Extensive experiments show that our proposed model improves the construction of all three graph types across in-domain, OOD and counter-task data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_11227 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | GKG-LLM: A Unified Framework for Generalized Knowledge Graph Construction Zhang, Jian Wei, Bifan Qi, Shihao Zhu, haiping Liu, Jun Lin, Qika Artificial Intelligence The construction of Generalized Knowledge Graph (GKG), including knowledge graph, event knowledge graph and commonsense knowledge graph, is fundamental for various natural language processing tasks. Current studies typically construct these types of graph separately, overlooking holistic insights and potential unification that could be beneficial in computing resources and usage perspectives. However, a key challenge in developing a unified framework for GKG is obstacles arising from task-specific differences. In this study, we propose a unified framework for constructing generalized knowledge graphs to address this challenge. First, we collect data from 15 sub-tasks in 29 datasets across the three types of graphs, categorizing them into in-sample, counter-task, and out-of-distribution (OOD) data. Then, we propose a three-stage curriculum learning fine-tuning framework, by iteratively injecting knowledge from the three types of graphs into the Large Language Models. Extensive experiments show that our proposed model improves the construction of all three graph types across in-domain, OOD and counter-task data. |
| title | GKG-LLM: A Unified Framework for Generalized Knowledge Graph Construction |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2503.11227 |