大模型与知识图谱互增技术与应用综述

doi:10.11896/jsjkx.250700129

Abstract

Abstract: With the development of artificial intelligence,the capabilities of large language models(LLMs) and knowledge graphs(KGs) in the field of natural language processing gained a lot of attention.Endowed with robust natural language understanding and generation capacities,LLMs have exhibited prominent emergent abilities in tasks including open-domain question answering and text generation.Nevertheless,LLMs are confronted with challenges such as inadequate interpretability and the existence of hallucinations in knowledge representation.Similarly,knowledge graphs provide interpretable symbolic support for complex reasoning and decision-making through structured knowledge representation,yet suffer from high construction costs and incomplete content.Therefore,the mutual enhancement technology of large language models and knowledge graphs has become a key research direction.This paper systematically reviews the relevant knowledge of large language models and knowledge graphs and introduces the mutual enhancement technologies between large language models and knowledge graphs,including knowledge graph-enhanced large models,large language model-enhanced knowledge graphs,and the mutual enhancement and collaboration between large language models and knowledge graphs.Additionally,it elaborates on the application of this synergistic framework.Finally,it summarizes the challenges and prospects of the mutually reinforced large language model-knowledge graph system,providing references for subsequent studies of this technology.

Key words: Large language model, Knowledge graph, Mutual enhancement and synergy, Natural language processing, Explicable

CLC Number:

TP391.1

JIA Zishuo, ZHANG Jian’ge, HE Haofeng, FENG Shizhong, LIU Yilin. Survey on Mutually Augmenting Technologies and Applications of Large Models and KnowledgeGraphs[J].Computer Science, 2026, 53(8): 219-228.

References

[1] RADFORD A,NARASIMHAN K,SALIMANS T,et al.Improving language understanding by generative pre-training[EB/OL].https://www.mikecaptain.com/resources/pdf/GPT-1.pdf.
[2] TOUVRON H,LAVRIL T,IZACARD G,et al.LLaMA:Open and Efficient Foundation Language Models[J].arXiv:2302.13971,2023.
[3] WEI J,TAY Y,BOMMASANI R,et al.Emergent abilities oflarge language models[J].arXiv:2206.07682,2022.
[4] FENSEL D,ŞIMŞEK U,ANGELE K,et al.Introduction:What is a Knowledge Graph?[C]//Knowledge Graphs:Methodology,Tools and Selected Use Cases.Cham:Springer,2020:1-10.
[5] LAVRINOVICS E,BISWAS R,BJERVA J,et al.KnowledgeGraphs,Large Language Models,and Hallucinations:An NLP Perspective[J].Web Semantics:Science,Services and Agents on the World Wide Web,2025,85:100844.
[6] DANILEVSKY M,QIAN K,AHARONOV R,et al.A Survey of the State of Explainable AI for Natural Language Processing[C]//Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing.2020:447-459.
[7] GUO D,YANG D,ZHANG H,et al.Deepseek-R1:Incentivizing Reasoning Capability in LLMs Via Reinforcement Learning[J].arXiv:2501.12948,2025.
[8] VASWANI A,SHAZEER N,PARMAR N,et al.Attention isall you need[C]//Proceedings of the 31st Internatioanl Confe-rence on Neural Information Processing Systems.2017:6000-6010.
[9] ACHIAM J,ADLER S,AGARWAL S,et al.Gpt-4 technical report[J].arXiv:2303.08774,2023.
[10] CHOWDHERY A,NARANG S,DEVLIN J,et al.Palm:Scaling language modeling with pathways[J].Journal of Machine Learning Research,2023,24(240):1-113.
[11] DEVLIN J,CHANG M W,LEE K,et al.Bert:Pretraining ofdeep bidirectional transformers for language understanding[J].arXiv:1810.04805,2018.
[12] ROUMELIOTIS K I,TSELIKAS N D.Chatgpt and open-aimodels:A preliminary review[J].Future Internet,2023,15(6):192.
[13] HURST A,LERER A,GOUCHER A P,et al.Gpt-4o system card[J].arXiv:2410.21276,2024.
[14] YANG Z,LI L,LIN K,et al.The Dawn of LMMs:Preliminary Explorations with GPT-4v(ision)[J].arXiv:2309.17421,2023.
[15] BETKER J,GOH G,LI J,et al.Improving image generationwith better captions[J].Computer Science,2023,2(3):8.
[16] LECUN Y,BOSER B,DENKER J S,et al.Backpropagation applied to handwritten zip code recognition[J].Neural Computation,1989,1(4):541-551.
[17] LECUN Y,BOTTOU L,BENGIO Y,et al.Gradient-basedlearning applied to document recognition[J].Proceedings of the IEEE,2002,86(11):2278-2324.
[18] JAECH A,KALAI A,LERER A,et al.OpenAI o1 system card[J].arXiv:2412.16720,2024.
[19] JI S X,PAN S R,ERIK C,et al.A Survey on KnowledgeGraphs:Representation,Acquisition,and Applications[J].IEEE Transactions on Neural Networks and Learning Systems,2021,33(2):494-514.
[20] MELNYK I,PIERRE D,PAYEL D.Grapher:Multi-stageknowledge graph construction using pretrained language models[C]//NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications.2021.
[21] SUN Y,WANG S,FENG S,et al.ERNIE 3.0:Large-scaleKnowledge Enhanced Pre-training for Language Understanding and Generation[J].arXiv.2112.12731,2021.
[22] LIU W,ZHOU P,ZHAO Z,et al.K-BERT:Enabling Language Representation with Knowledge Graph[J].Proceedings of the AAAI Conference on Artificial Intelligence,2020,34(3):2901-2908.
[23] LEWIS P,PEREZ E,PIKTUS A,et al.Retrieval-AugmentedGeneration for Knowledge-Intensive NLP Tasks[J].arXiv.2005.11401,2020.
[24] TANG Y,ZHANG J,YU Z,et al.Mips-fusion:Multi-implicit-submaps for scalable and robust online neural rgb-d reconstruction[J].ACM Transactions on Graphics,2023,42(6):1-16.
[25] SUTSKEVER I,VINYALS O,LE Q V.Sequence to sequence learning with neural networks[J].arXiv:1409.3215,2014.
[26] BAEK J,AJI A F,SAFFARI A.Knowledge-Augmented Language Model Prompting for Zero-Shot Knowledge Graph Question Answering[J].arXiv.2306.04136,2023.
[27] SUN T,SHAO Y,QIU X,et al.CoLAKE:Contextualized language and knowledge embedding[C]//Proceedings of the 28th International Conference on Computational Linguistics.2020:3660-3670.
[28] LI Y,SONG D,ZHOU C,et al.A Framework of Knowledge Graph-Enhanced Large Language Model Based on Question Decomposition and Atomic Retrieval[C]//Findings of the Association for Computational Linguistics(EMNLP 2024).2024:11472-11485.
[29] LIN B Y,CHEN X,CHEN J,et al.KagNet:Knowledgeaware graph networks for commonsense reasoning[C]//EMNLPIJCNLP.2019:2829-2839.
[30] LIU H C,WANG S,ZHU Y C,et al.Knowledge Graph-Enhanced Large Language Models via Path Selection[C]//Fin-dings of the Association for Computational Linguistics:ACL 2024.2024:6311-6321.
[31] ZHANG T,WANG C,HU N,et al.DKPLM:decomposableknowledge-enhanced pre-trained language model for natural language understanding[C]//AAAI.2022:11703-11711.
[32] DAI D,DONG L,HAO Y,et al.Knowledge neurons in pretrained transformers[J] arXiv:2104.08696,2021.
[33] LI S,LI X,SHANG L,et al.How pre-trained language models capture factual knowledge? a causal-inspired analysis[J].arXiv:2203.16747,2022.
[34] SWAMY V,ROMANOU A,JAGGI M.Interpreting language models through knowledge graph extraction[J].arXiv:2111.08546,2021.
[35] ZHANG M,YE X,LIU Q,et al.Knowledge graph enhanced large language model editing[J].arXiv:2402.13593,2024.
[36] KONG W Q.A Framework of Constructing Domain KnowledgeGraph Based on LLM Prompt[D].Chengdu:University of Electronic Science and Technology of China,2024.
[37] LAI Q N,JIN J D,ZHOU C L.Research on knowledge graph construction technology for cyberthreat intelligence based on large language models[J].Journal on Communications,2024,45(S2):33-43.
[38] CAO L,SUN J M,CROSS A.An Automatic and End-to-End System for Rare Disease Knowledge Graph Construction Based on Ontology-Enhanced Large Language Models:Development Study[J].arXiv:2403.00953,2024.
[39] XIE M H.Automatic Construction and Retrieval of Knowledge Graph inElectronic Information Field Based on Large Language Model(LLM)[J].Telecommunication Engineering,2024,64(8):1228-1234.
[40] HU E J,SHEN Y,WALLIS P,et al.LoRA:Low-Rank Adapta-tion of Large Language Models[J].arXiv:2106.09685,2021.
[41] CAO Y X.Knowledge Graph Completion:Terminology Release[EB/OL].https://www.ccf.org.cn/Media_list/gzwyh/jsjsysdwyh/2022-01-07/789837.shtml.
[42] LIU W,ZHOU P,ZHAO Z,et al.K-BERT:enabling language representation with knowledge graph[C]//AAAI.2020:2901-2908.
[43] ZHANG H C,LI Q Y,YANG L,et al.Knowledge Graph Completion Method Based on Contrastive Learning and Language Model Enhanced Embedding[J].Computer Engineering,2024,50(4):168-176.
[44] WANG B,SHEN T,LONG G,et al.Structure-augmented text representation learning for efficient knowledge graph completion[C]//Proceedings of the Web Conference 2021.2021:1737-1748.
[45] WANG L,ZHAO W,WEI Z,et al.Simkgc:Simple contrastive knowledge graph completion with pre-trained language models[J].arXiv:2203.02167,2022.
[46] YANG R,ZHU J,MAN J,et al.Enhancing text-based know-ledge graph completion with zero-shot large language models:A focus on semantic enhancement[J].Knowledge-Based Systems,2024,300:112155.
[47] CAI Q H,XU B,DONG X D.Knowledge Graph Completion Model Using Semantically Enhanced Prompts and Structural Information[J].Computer Science,2025,52(9):282-293.
[48] CHEN Z,BAI L,LI Z,et al.A new pipeline for knowledge graph reasoning enhanced by large language models without fine-tuning[C]//Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing.2024:1366-1381.
[49] ZHENG Y Z,ZHU D J,WU H L,et al.Overview on Knowledge Graph Question Answering[J].Computer Systems & Applications,2022,31(4):1-13.
[50] BAI Y T,HAO W Y,JIN D W,et al.Study on KnowledgeGraph Question Answering Methods Incorporating External Knowledge[J].Software Guide,2024,23(9):56-62.
[51] FENG T,HE L.RGR-KBQA:Generating Logical Forms for Question Answering Using Knowledge-Graph-Enhanced Large Language Model[C]//Proceedings of the 31st International Conference on Computational Linguistics.2025:3057-3070.
[52] XIE F,SONG J H,JIANG L,et al.Large model enhancedknowledge graph question answering model for blockchainvulnerability knowledge base[J].Modern Electronics Technique,2025,48(2):137-142.
[53] ZHOU T,CHEN Y,LIU K,et al.CogMG:Collaborative Augmentation Between Large Language Model and Knowledge Graph[J].arXiv:2406.17231,2024.
[54] SHI Y,JIANG G,QIU T,et al.AgentRE:An Agent-BasedFramework for Navigating Complex Information Landscapes in Relation Extraction[C]//Proceedings of the 33rd ACM International Conference on Information and Knowledge Management.2024:2045-2055.
[55] JIANG J,ZHOU K,ZHAO W X,et al.Kg-agent:An efficient autonomous agent framework for complex reasoning over knowledge graph[J].arXiv:2402.11163,2024.
[56] XIE W,HUANG J Y,CHENG B,et al.Complex logical reasoning methods for knowledge graphs based on large language mo-dels[C]//Proceedings of the 39th National Conference on Computer Security Academic Exchange.Beijing:Journal of Information Security Research,2024:175-180.
[57] LI Y,ZHANG R,LIU J.An enhanced prompt-based llm reasoning scheme via knowledge graph-integrated collaboration[C]//International Conference on Artificial Neural Networks.Cham:Springer,2024:251-265.
[58] ZHANG Z,HAN X,LIU Z,et al.ERNIE:Enhanced language representation with informative entities[J].arXiv:1905.07129,2019.
[59] WANG X,GAO T,ZHU Z,et al.KEPLER:A unified model for knowledge embedding and pre-trained language representation[J].Transactions of the Association for Computational Linguistics,2021,9:176-194.
[60] CHEN Y.Temporal Knowledge Graph Link Prediction usingSynergized Large Language Models and Temporal Knowledge Graphs[D].Guangzhou:Guangdong University of Foreign Stu-dies,2024.
[61] XU J,PAN X,SHE X Y.Intelligent integration method of cultural and tourism knowledge based on knowledge graphs and large language models[J].Journal of Jilin Normal University(Natural Science Edition),2025,46(1):111-116.
[62] XIE F.Research on Blockchain Vulnerability Intelligent Question Answering by Integrating Knowledge Graph with Large Language Models[D].Wuhan:Hubei University,2024.
[63] JIA M,DUAN J,SONG Y,et al.medIKAL:Integrating knowledge graphs as assistants of LLMs for enhanced clinical diagnosis on EMRs[J].arXiv:2406.14326,2024.
[64] CHEN J,ZHAO X C,SUI J Y,et al.Narrative-Driven Large Language Model for Temporal Knowledge Graph Prediction[J].Pattern Recognition and Artificial Intelligence,2024,37(8):715-728.
[65] LI J,ZHU G J,WANG A,et al.Knowledge-Enhanced Large Language Models for Urban Transportation:Modeling and Applications[J].Urban Transport of China,2025,23(2):1-12,38.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

Comments

Recommended 0

No Suggested Reading articles found!

Survey on Mutually Augmenting Technologies and Applications of Large Models and KnowledgeGraphs

PDF (PC)

Abstract

Cite this article

share this article

References

Related Articles 15

Metrics

Comments

Recommended 0

[1]	LIU Jing. Review of Music Artificial Intelligence Driven by Large Language Models [J]. Computer Science, 2026, 53(8): 229-244.
[2]	QUAN Jingtao, ZHANG Lei, LIU Bailong, WANG Feifan. Leveraging Multi-source Contextual Knowledge-enhanced Graph for Traffic Forecasting [J]. Computer Science, 2026, 53(8): 245-256.
[3]	ZHANG Haoran, HAO Wenning, JIN Dawei, CHENG Kai, LIU Junyang. Agentic Retrieval Augmented Generation Framework Based on Retrieval Task Planning and Reflection Mechanism [J]. Computer Science, 2026, 53(8): 285-297.
[4]	ZHANG Zhonglin, XIA Hang. LSQ-RAG:Retrieval-enhanced Generation Framework Based on LLM-enhanced Ranker [J]. Computer Science, 2026, 53(8): 298-306.
[5]	MAO Yixiao, WANG Zixiao, ZHANG Baili, ZONG Shaohao. Element-aware Screening Method for Popularization Cases [J]. Computer Science, 2026, 53(8): 316-325.
[6]	FAN Ruxin, SUN Baicai, GONG Lina, YAO Xiangjuan, GONG Dunwei. Test Case Generation and Prioritization for Program Fault Diagnosis Based on Large LanguageModel [J]. Computer Science, 2026, 53(8): 365-374.
[7]	WANG Xinlin, LI Yan, MA Chaofan, LI Shuo. Retrieval-Augmented Generation:Survey of Methods and Applications [J]. Computer Science, 2026, 53(7): 101-117.
[8]	CHEN Zhixiang, XIE Zhipeng. Event Causal Data Augmentation Method Based on Large Language Model [J]. Computer Science, 2026, 53(7): 125-131.
[9]	XU Rui, LIU Jin, LIU Xudong, GUAN Jian, DONG Wei. Exploring the Generalization Ability of Prompt-based Large Language Models for TextClassification [J]. Computer Science, 2026, 53(6A): 250400092-7.
[10]	WEI Qing, ZHANG Yupeng, LIU Shaoxun, ZHANG Jinfeng, ZHANG Yuezhong, CHEN Haoyang. Fuzzing Driver Generation Based on Large Language Models [J]. Computer Science, 2026, 53(6A): 250400113-8.
[11]	SHEN Jianwei, CHEN Jiawen, CHEN Hanlin, MA Xinjian, CHEN Xing. Construction and Application of Dataset Knowledge Graph Based on Metadata Semantic Enhancement [J]. Computer Science, 2026, 53(6A): 250500052-10.
[12]	ZHANG Yongyu, GUO Chenjuan, FEI Xueqin, LI Feng. Study on Financial Text Sentiment Analysis Method Based on Large Language Models with Market Feedback Supervision [J]. Computer Science, 2026, 53(6A): 250500073-14.
[13]	CHU Xiaolong, DU Jinlian, LUO Fangyuan, JIN Xueyun. Design and Application of Semantic Model for Medical Record Knowledge Graph Querying [J]. Computer Science, 2026, 53(6A): 250900023-9.
[14]	XU Yafei, LIU Chuanyou, LIU Shaohua. Study on Text-to-SQL Approach Integrating Chain-of-Thought Reasoning with Retrieval Augmentation [J]. Computer Science, 2026, 53(6A): 250900107-7.
[15]	LIU Jiaqi, GAO Zhizezhang, MENG Xianjia, SUN Xia, FENG Jun. Automatic Knowledge Point Annotation for Student Code Based on Multi-agent Collaboration:A Case Study of C Language [J]. Computer Science, 2026, 53(6): 59-68.