大语言模型驱动下知识图谱的构建及应用综述OA
A Survey on the Construction and Application of Knowledge Graphs Driven by Large Language Models
在大语言模型的助力下,知识图谱凭借结构化和语义丰富的特征,提升了数据关联与解释能力,为复杂知识推理和智能决策支持等领域提供了新的研究方向和应用潜力.从知识图谱的角度出发,总结了大语言模型驱动下知识图谱的构建及应用的最新研究进展.首先,从知识建模、信息抽取、知识融合以及知识图谱补全等角度探讨了知识图谱构建的新方法;其次,阐述了知识图谱在增强大语言模型、提升检索能力以及与大语言模型协同增强三个方面的应用;最后,对大语言模型与知识图谱结合的未来研究方向进行了展望.
With the support of large language models,knowledge graphs,characterized by their struc-tured and semantically rich features,enhanced data association and interpretability.This provided new research directions and application potential for complex knowledge reasoning and intelligent decision-making.Therefore,from the perspective of knowledge graphs,the latest progress in the construction and application of knowledge graphs driven by large language models was summarized.Firstly,the new meth-ods for building knowledge graphs were explored from the perspectives of knowledge modeling,informa-tion extraction,knowledge integration,and knowledge graph completion.Secondly,the applications of knowledge graphs in augmenting large language models,improving retrieval capabilities,and achieving mutual enhancement with large language models were investigated.Finally,the future directions of com-bining large language models with knowledge graphs were discussed.
张坤丽;王影;付文慧;朱永其;张艳莉;昝红英
郑州大学 计算机与人工智能学院 河南 郑州 450001郑州大学 计算机与人工智能学院 河南 郑州 450001郑州大学 计算机与人工智能学院 河南 郑州 450001郑州大学 计算机与人工智能学院 河南 郑州 450001郑州大学 网络空间安全学院 河南 郑州 450002郑州大学 计算机与人工智能学院 河南 郑州 450001
信息技术与安全科学
大语言模型知识图谱信息抽取协同增强
large language modelknowledge graphinformation extractionmutual enhancement
《郑州大学学报(理学版)》 2026 (2)
1-9,9
国家自然科学基金项目(U23A20316)河南省科技厅科技攻关项目(232102211039)信息网络安全公安部重点实验室开放课题项目(C23600-04)
评论