Efficient Knowledge Infusion via KG-LLM Alignment

Zhouyu Jiang, Ling Zhong, Mengshu Sun, Jun Xu, Rui Sun, Hui Cai, Shuhan Luo, Zhiqiang Zhang


Abstract
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 strategy to 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.
Anthology ID:
2024.findings-acl.176
Volume:
Findings of the Association for Computational Linguistics: ACL 2024
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Lun-Wei Ku, Andre Martins, Vivek Srikumar
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2986–2999
Language:
URL:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-acl.176/
DOI:
10.18653/v1/2024.findings-acl.176
Bibkey:
Cite (ACL):
Zhouyu Jiang, Ling Zhong, Mengshu Sun, Jun Xu, Rui Sun, Hui Cai, Shuhan Luo, and Zhiqiang Zhang. 2024. Efficient Knowledge Infusion via KG-LLM Alignment. In Findings of the Association for Computational Linguistics: ACL 2024, pages 2986–2999, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
Efficient Knowledge Infusion via KG-LLM Alignment (Jiang et al., Findings 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/build-pipeline-with-new-library/2024.findings-acl.176.pdf