Efficient Knowledge Infusion via KG-LLM Alignment
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_ | 1866909218274017280 |
|---|---|
| author | Jiang, Zhouyu Zhong, Ling Sun, Mengshu Xu, Jun Sun, Rui Cai, Hui Luo, Shuhan Zhang, Zhiqiang |
| author_facet | Jiang, Zhouyu Zhong, Ling Sun, Mengshu Xu, Jun Sun, Rui Cai, Hui Luo, Shuhan Zhang, Zhiqiang |
| contents | To tackle the problem of domain-specific knowledge scarcity within large language models (LLMs), knowledge graph-retrievalaugmented method has been proven to be an effective and efficient technique for knowledge infusion. However, existing approaches face two primary challenges: knowledge mismatch between public available knowledge graphs and the specific domain of the task at hand, and poor information compliance of LLMs with knowledge graphs. In this paper, we leverage a small set of labeled samples and a large-scale corpus to efficiently construct domain-specific knowledge graphs by an LLM, addressing the issue of knowledge mismatch. Additionally, we propose a three-stage KG-LLM alignment strategyto enhance the LLM's capability to utilize information from knowledge graphs. We conduct experiments with a limited-sample setting on two biomedical question-answering datasets, and the results demonstrate that our approach outperforms existing baselines. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_03746 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Efficient Knowledge Infusion via KG-LLM Alignment Jiang, Zhouyu Zhong, Ling Sun, Mengshu Xu, Jun Sun, Rui Cai, Hui Luo, Shuhan Zhang, Zhiqiang Computation and Language Artificial Intelligence To tackle the problem of domain-specific knowledge scarcity within large language models (LLMs), knowledge graph-retrievalaugmented method has been proven to be an effective and efficient technique for knowledge infusion. However, existing approaches face two primary challenges: knowledge mismatch between public available knowledge graphs and the specific domain of the task at hand, and poor information compliance of LLMs with knowledge graphs. In this paper, we leverage a small set of labeled samples and a large-scale corpus to efficiently construct domain-specific knowledge graphs by an LLM, addressing the issue of knowledge mismatch. Additionally, we propose a three-stage KG-LLM alignment strategyto enhance the LLM's capability to utilize information from knowledge graphs. We conduct experiments with a limited-sample setting on two biomedical question-answering datasets, and the results demonstrate that our approach outperforms existing baselines. |
| title | Efficient Knowledge Infusion via KG-LLM Alignment |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2406.03746 |