Efficient Knowledge Infusion via KG-LLM Alignment

Anonymous

Abstract: To tackle the problem of domain-specific knowledge scarcity within large language models(LLMs), knowledge graph-retrieval-augmented 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 LLM 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 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.

Paper Type: long

Research Area: Efficient/Low-Resource Methods for NLP

Contribution Types: NLP engineering experiment, Approaches to low-resource settings

Languages Studied: English, Chinese