A fusion inference method for large language models and knowledge graphs based on structured injection and causal inference
Xueyang Xing, Bo Jia, Zhicheng Huang, Yongzhi Chen, Junjie Wang, Anfei Fan, Xin Chen, Lei Cao · 2023
In this paper, we propose a large language model and knowledge graph fusion reasoning method based on structured injection and causal reasoning (LKFSC) to address the limitations of existing large language models and knowledge graphs in practical applications. The approach effectively mitigates the problems of long-distance dependency and limited contextual information, and improves the reasoning capability of the large language model. Meanwhile, by fusing the generative ability of the large language model and the inference ability of the knowledge graph, the method realizes intelligent reasoning for complex problems. The main contributions of this paper include proposing a structured injection method that introduces causality for reasoning, and constructing a fusion reasoning framework that effectively mitigates the illusory problem of large language models and provides powerful and intelligent decision support for practical applications.