| 3,086 | 2 | 293 |
| 下载次数 | 被引频次 | 阅读次数 |
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。
Abstract：With the support of large language models, knowledge graphs, characterized by their structured 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 methods for building knowledge graphs were explored from the perspectives of knowledge modeling, information 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 combining large language models with knowledge graphs were discussed.
[1] SHANAHAN M.Talking about large language models[J].Communications of the ACM,2024,67(2):68-79.
[2] PENG C Y,XIA F,NASERIPARSA M,et al.Knowledge graphs:opportunities and challenges[J].Artificial intelligence review,2023,56(11):13071-13102.
[3] BOSSELUT A,RASHKIN H,SAP M,et al.COMET:commonsense transformers for automatic knowledge graph construction[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.Stroudsburg:Association for Computational Linguistics,2019:4762-4779.
[4] ZHANG Z S,ZHANG A,LI M,et al.Automatic chain of thought prompting in large language models[EB/OL].(2024-03-04)[2024-09-10].https://doi.org/10.48550/arXiv.2210.03493.
[5] WANG X,ZHOU W K,ZU C,et al.InstructUIE:multi-task instruction tuning for unified information extraction[EB/OL].(2024-03-04)[2024-09-10].https://doi.org/10.48550/arXiv.2304.08085.
[6] YAO L,PENG J Z,MAO C S,et al.Exploring large language models for knowledge graph completion[EB/OL].(2023-04-17)[2024-09-10].https://doi.org/10.48550/arXiv.2308.13916.
[7] WEN Y L,WANG Z F,SUN J M.MindMap:knowledge graph prompting sparks graph of thoughts in large language models[C]//Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics.Stroudsburg:Association for Computational Linguistics,2024:10370-10388.
[8] BAEK J,AJI A F,SAFFARI A.Knowledge-augmented language model prompting for zero-shot knowledge graph question answering[C]//Proceedings of the 1st Workshop on Natural Language Reasoning and Structured Explanations.Stroudsburg:Association for Computational Linguistics,2023:78-106.
[9] 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].JMIR medical informatics,2024,12:e60665.
[10] NEUHAUS F.Ontologies in the era of large language models:a perspective[J].Applied ontology,2023,18(4):399-407.
[11] COHEN R,GEVA M,BERANT J,et al.Crawling the internal knowledge-base of language models[C]//Findings of the Association for Computational Linguistics:EACL 2023.Stroudsburg:Association for Computational Linguistics,2023:1856-1869.
[12] FUNK M,HOSEMANN S,JUNG J C,et al.Towards ontology construction with language models[EB/OL].(2024-03-04)[2024-09-10].https://doi.org/10.48550/arXiv.2309.09898.
[13] XIA Y,ZHAO Y W,WU W H,et al.Debiasing generative named entity recognition by calibrating sequence likelihood[C]//Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics.Stroudsburg:Association for Computational Linguistics,2023:1137-1148.
[14] XIE T Y,LI Q,ZHANG Y,et al.Self-improving for zero-shot named entity recognition with large language models[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.Stroudsburg:Association for Computational Linguistics,2024:583-593.
[15] MA Y B,CAO Y X,HONG Y,et al.Large language model is not a good few-shot information extractor,but a good reranker for hard samples![C]//Findings of the Association for Computational Linguistics:EMNLP 2023.Stroudsburg:Association for Computational Linguistics,2023:10572-10601.
[16] RUBIN O,HERZIG J,BERANT J.Learning to retrieve prompts for in-context learning[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.Stroudsburg:Association for Computational Linguistics,2022:2655-2671.
[17] ASHOK D,LIPTON Z C.PromptNER:prompting for named entity recognition [EB/OL].(2023-06-20)[2024-09-10].https://doi.org/10.48550/arXiv.2305.15444.
[18] PAOLINI G,ATHIWARATKUN B,KRONE J,et al.Structured prediction as translation between augmented natural languages [EB/OL].(2021-01-14)[2024-09-10].https://doi.org/10.48550/arXiv.2101.05779.
[19] ZHANG K,JIMENEZ G B,SU Y.Aligning instruction tasks unlocks large language models as zero-shot relation extractors[C]//Findings of the Association for Computational Linguistics:ACL 2023.Stroudsburg:Association for Computational,2023:794-812.
[20] LU Y J,LIU Q,DAI D,et al.Unified structure generation for universal information extraction[C]//Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics.Stroudsburg:Association for Computational,2022:5755-5772.
[21] WEI X,CUI X Y,CHENG N,et al.Zero-shot information extraction via chatting with ChatGPT[EB/OL].(2024-05-27)[2024-09-10].https://doi.org/10.48550/arXiv.2302.10205.
[22] GUO Y C,LI Z X,JIN X L,et al.Retrieval-augmented code generation for universal information extraction[M]//Natural Language Processing and Chinese Computing.Berlin:Springer Press,2024:30-42.
[23] BI Z,CHEN J,JIANG Y N,et al.CodeKGC:code language model for generative knowledge graph construction[J].ACM transactions on Asian and low-resource language information processing,2024,23(3):1-16.
[24] SAINZ O,GARCÍA-FERRERO I,AGERRI R,et al.GoLLIE:annotation guidelines improve zero-shot information-extraction[EB/OL].(2024-05-06) [2024-09-10].https://doi.org/10.48550/arXiv.2310.03668.
[25] YUAN Z D,HU S B,VULI■,et al.Can pretrained language models (Yet) reason deductively?[C]//Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics.Stroudsburg:Association for Computational Linguistics,2023:1447-1462.
[26] BALDAZZI T,BELLOMARINI L,CERI S,et al.Fine-tuning large enterprise language models via ontological reasoning[C]//Proceedings of the 17th Linguistic Annotation Workshop.Cham:Springer International Publishing,2023:86-94.
[27] STRAKOVA J,FUCIKOVA E,HAJIC J,et al.Extending an event-type ontology:adding verbs and classes using fine-tuned LLMs suggestions[C]//Proceedings of the 17th Linguistic Annotation Workshop.Stroudsburg:Association for Computational Linguistics,2023:85-95.
[28] 李卫军，顾建来，张新勇，等.基于关系学习的小样本知识图谱补全模型[J].郑州大学学报(工学版),2024,45(4):53-61.LI W J,GU J L,ZHANG X Y,et al.Relation learning completion model for few-shot knowledge graphs[J].Journal of Zhengzhou university (engineering science),2024,45(4):53-61.
[29] ZHAO W X,ZHOU K,LI J,et al.A survey of large language models[EB/OL].(2024-05-27) [2024-09-10].https://doi.org/10.48550/arXiv.2302.10205.
[30] XIE X,LI Z B,WANG X H,et al.LambdaKG:a library for pre-trained language model-based knowledge graph embeddings[C]//Proceedings of the 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics:System Demonstrations.Stroudsburg:Association for Computational Linguistics,2023:25-33.
[31] WEI Y B,HUANG Q S,ZHANG Y,et al.KICGPT:large language model with knowledge in context for knowledge graph completion[C]//Findings of the Association for Computational Linguistics:EMNLP 2023.Stroudsburg:Association for Computational Linguistics,2023:8667-8683.
[32] SHU D,CHEN T L,JIN M Y,et al.Knowledge graph large language model (KG-LLM) for link prediction[EB/OL].(2024-08-09)[2024-09-10].https://doi.org/10.48550/arXiv.2403.07311.
[33] XU D R,ZHANG Z H,LIN Z X,et al.Multi-perspective improvement of knowledge graph completion with large language models[C]//Proceedings of the Joint International Conference on Computational Linguistics,Language Resources and Evaluation.Stroudsburg:Association for Computational Linguistics,2024:11956-11968.
[34] LI D W,TAN Z,CHEN T L,et al.Contextualization distillation from large language model for knowledge graph completion[C]//Findings of the Association for Computational Linguistics:EACL 2024.Stroudsburg:Association for Computational Linguistics,2024:458-477.
[35] MALLEN A,ASAI A,ZHONG V,et al.When not to trust language models:investigating effectiveness of parametric and non-parametric memories[C]//Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics.Stroudsburg:Association for Computational Linguistics,2023:9802-9822.
[36] CHEN W H,SU Y,YAN X F,et al.KGPT:knowledge-grounded pre-training for data-to-text generation[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing.Stroudsburg:Association for Computational Linguistics,2020:8635-8648.
[37] SUN Y,WANG S H,FENG S K,et al.ERNIE 3.0:large-scale knowledge enhanced pre-training for language understanding and generation[EB/OL].(2021-07-05)[2024-09-10].https://doi.org/10.48550/arXiv.2107.02137.
[38] ROSSET C,XIONG C Y,PHAN M,et al.Knowledge-aware language model pretraining [EB/OL].(2022-10-07)[2024-09-10].https://doi.org/10.48550/arXiv.2210.03493.
[39] WANG X Z,GAO T Y,ZHU Z C,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.
[40] MCCOY T,PAVLICK E,LINZEN T.Right for the wrong reasons:diagnosing syntactic heuristics in natural language inference[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.Stroudsburg:Association for Computational Linguistics,2019:3428-3448.
[41] THOPPILAN R,FREITAS D,HALL J,et al.LaMDA:language models for dialog applications[EB/OL].(2022-02-10)[2024-09-10].https://doi.org/10.48550/arXiv.2201.08239.
[42] LI S Y,GAO Y F,JIANG H M,et al.Graph reasoning for question answering with triplet retrieval[C]//Findings of the Association for Computational Linguistics:ACL 2023.Stroudsburg:Association for Computational Linguistics,2023:3366-3375.
[43] WEI J,WANG X Z,SCHUURMANS D,et al.Chain-of-thought prompting elicits reasoning in large language models[C]//Proceedings of the 36th International Conference on Neural Information Processing Systems.New York:ACM Press,2024:24824-24837.
[44] GUAN Z H,WU Z H,LIU Z,et al.CohortGPT:an enhanced GPT for participant recruitment in clinical study[EB/OL].(2023-07-21)[2024-09-10].https://doi.org/10.48550/arXiv.2307.11346.
[45] WANG J N,SUN Q S,LI X,et al.Boosting language models reasoning with chain-of-know-ledge prompting[EB/OL].(2024-07-03)[2024-09-10].https://doi.org/10.48550/arXiv.2306.06427.
[46] CHEN Z C,CHEN J D,GAIDHANI M,et al.XplainLLM:a knowledge-augmented dataset for understanding llm decision-making [EB/OL].(2024-09-20)[2024-10-10].https://doi.org/10.48550/arXiv.2311.08614.
[47] SHI G S,DENG X F,LUO L H,et al.LLM-powered explanations:unraveling recommendations through subgraph reasoning[EB/OL].(2024-07-30)[2024-10-10].https://doi.org/10.48550/arXiv.2406.15859.
[48] SHARIATMADARI A H,GUO S,SRINI V S,et al.Harnessing the power of knowledge graphs to enhance LLM explainability in the biomedical domain[C]//Proceedings of 1st AAAI Workshop on Large Language Models for Biological Discoveries.Palo Alto:AAAI Press,2024:1-8.
[49] MA S J,XU C J,JIANG X H,et al.Think-on-graph 2.0:deep and interpretable large language model reasoning with knowledge graph-guided retrieval[EB/OL].(2024-08-06)[2024-09-10].https://doi.org/10.48550/arXiv.2407.10805.
[50] YE X,YAVUZ S,HASHIMOTO K,et al.RNG-KBQA:generation augmented iterative ranking for knowledge base question answering[C]//Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics.Stroudsburg:Association for Computational Linguistics,2022:6032-6043.
[51] LIU Y,YAVUZ S,MENG R,et al.Uni-Parser:unified semantic parser for question answering on knowledge base and database[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing.Stroudsburg:Association for Computational Linguistics,2022:8858-8869.
[52] YU D H,ZHANG S,NG P,et al.DecAF:joint decoding of answers and logical forms for question answering over knowledge bases[EB/OL].(2022-09-30)[2024-09-10].https://doi.org/10.48550/arXiv.2210.00063.
[53] OGUZ B,CHEN X L,KARPUKHIN V,et al.UniK-QA:unified representations of structured and unstructured knowledge for open-domain question answering[C]//Findings of the Association for Computational Linguistics:NAACL 2022.Stroudsburg:Association for Computational Linguistics,2022:1535-1546.
[54] KE P,JI H Z,RAN Y,et al.JointGT:graph-text joint representation learning for text generation from knowledge graphs[C]//Findings of the Association for Computational Linguistics:ACL-IJCNLP 2021.Stroudsburg:Association for Computational Linguistics,2021:2526-2538.
[55] YASUNAGA M,BOSSELUT A,REN H Y,et al.Deep bidirectional language-knowledge graph pretraining[C]//Proceedings of the 36th International Conference on Neural Information Processing Systems.New York:ACM Press,2024:37309-37323.
[56] FENG Y L,CHEN X Y,LIN B Y,et al.Scalable multi-hop relational reasoning for knowledge-aware question answering[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing.Stroudsburg:Association for Computational Linguistics,2020:1295-1309.
[57] YASUNAGA M,REN H Y,BOSSELUT A,et al.QA-GNN:reasoning with language models and knowledge graphs for question answering[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.Stroudsburg:Association for Computational Linguistics,2021:535-546.
[58] SUN Y Q,SHI Q,QI L,et al.JointLK:joint reasoning with language models and knowledge graphs for commonsense question answering[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.Stroudsburg:Association for Computational Linguistics,2022:5049-5060.
[59] PAN S R,LUO L H,WANG Y F,et al.Unifying large language models and knowledge graphs:a roadmap[J].IEEE transactions on knowledge and data engineering,2024,36(7):3580-3599.
基本信息:
DOI：10.13705/j.issn.1671-6841.2024165
中图分类号:TP391.1
引用信息:
[1]张坤丽,王影,付文慧,等.大语言模型驱动下知识图谱的构建及应用综述[J].郑州大学学报(理学版),2026,58(02):1-9.DOI:10.13705/j.issn.1671-6841.2024165.
基金信息:
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)
2025-04-17
2025-04-17
2025-04-17