{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T16:57:57Z","timestamp":1783702677267,"version":"3.55.0"},"reference-count":172,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T00:00:00Z","timestamp":1752624000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Comput. Sci."],"abstract":"<jats:p>The fusion of Knowledge Graphs (KGs) and Large Language Models (LLMs) leverages their complementary strengths to address limitations of both technologies. This paper explores integration practices, opportunities, and challenges, focusing on three strategies: KG-enhanced LLMs (KEL), LLM-enhanced KGs (LEK), and collaborative LLMs and KGs (LKC). The study reviews these methodologies, highlighting their potential to enhance knowledge representation, reasoning, and question answering. We comprehensively compile and categorize key challenges such as knowledge acquisition and real-time updates, providing valuable directions for future research. The paper also discusses emerging techniques and applications to advance the synergy between KGs and LLMs. Overall, this work offers a comprehensive overview of the current landscape and the transformative potential of KG-LLM fusion across various domains.<\/jats:p>","DOI":"10.3389\/fcomp.2025.1590632","type":"journal-article","created":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T05:37:22Z","timestamp":1752644242000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":13,"title":["Practices, opportunities and challenges in the fusion of knowledge graphs and large language models"],"prefix":"10.3389","volume":"7","author":[{"given":"Linyue","family":"Cai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chaojia","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongqi","family":"Kang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu","family":"Fu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heng","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,7,16]]},"reference":[{"key":"B1","article-title":"Knowledge graphs as context sources for llm-based explanations of learning recommendations","author":"Abu-Rasheed","year":"2024","journal-title":"arXiv preprint arXiv:2403.03008"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3290605.3300233","article-title":"\u201cGuidelines for human-ai interaction,\u201d","author":"Amershi","year":"2019","journal-title":"Proceedings of the 2019 Chi Conference on Human Factors in Computing Systems"},{"key":"B3","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1145\/3460231.3474243","article-title":"\u201cSparse feature factorization for recommender systems with knowledge graphs,\u201d","author":"Anelli","year":"2021","journal-title":"Proceedings of the 15th ACM Conference on Recommender Systems"},{"key":"B4","article-title":"Refined: an efficient zero-shot-capable approach to end-to-end entity linking","author":"Ayoola","year":"2022","journal-title":"arXiv preprint arXiv:2207.04108"},{"key":"B5","doi-asserted-by":"publisher","first-page":"610","DOI":"10.1145\/3442188.3445922","article-title":"\u201cOn the dangers of stochastic parrots: can language models be too big?\u201d","author":"Bender","year":"2021","journal-title":"Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency"},{"key":"B6","doi-asserted-by":"publisher","first-page":"83","DOI":"10.3233\/SW-222960","article-title":"Madlink: Attentive multihop and entity descriptions for link prediction in knowledge graphs","volume":"15","author":"Biswas","year":"2024","journal-title":"Semant. Web"},{"key":"B7","first-page":"26","article-title":"\u201cTranslating embeddings for modeling multi-relational data,\u201d","author":"Bordes","year":"2013","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B8","article-title":"Kgvalidator: a framework for automatic validation of knowledge graph construction","author":"Boylan","year":"2024","journal-title":"arXiv preprint arXiv:2404.15923"},{"key":"B9","first-page":"467","article-title":"Class-based n-gram models of natural language","volume":"18","author":"Brown","year":"1992","journal-title":"Comput. Linguist"},{"key":"B10","article-title":"Meg: medical knowledge-augmented large language models for question answering","author":"Cabello","year":"2024","journal-title":"arXiv preprint arXiv:2411.03883"},{"key":"B11","article-title":"Cdlm: Cross-document language modeling","author":"Caciularu","year":"2021","journal-title":"arXiv preprint arXiv:2101.00406"},{"key":"B12","doi-asserted-by":"publisher","first-page":"12032","DOI":"10.1007\/s10489-022-04123-w","article-title":"Relmkg: reasoning with pre-trained language models and knowledge graphs for complex question answering","volume":"53","author":"Cao","year":"2023","journal-title":"Appl. Intell"},{"key":"B13","doi-asserted-by":"publisher","first-page":"17772","DOI":"10.1609\/aaai.v38i16.29730","article-title":"\u201cIs a large language model a good annotator for event extraction?\u201d","author":"Chen","year":"2024","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"B14","article-title":"Entity alignment with noisy annotations from large language models","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv:2405.16806"},{"key":"B15","article-title":"Kgpt: Knowledge-grounded pre-training for data-to-text generation","author":"Chen","year":"2020","journal-title":"arXiv preprint arXiv:2010.02307"},{"key":"B16","article-title":"Llm-align: utilizing large language models for entity alignment in knowledge graphs","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv:2412.04690"},{"key":"B17","article-title":"Continual multimodal knowledge graph construction","author":"Chen","year":"2023","journal-title":"arXiv preprint arXiv:2305.08698"},{"key":"B18","doi-asserted-by":"publisher","first-page":"132025","DOI":"10.1109\/ACCESS.2021.3113329","article-title":"Mem-kgc: masked entity model for knowledge graph completion with pre-trained language model","volume":"9","author":"Choi","year":"2021","journal-title":"IEEE Access"},{"key":"B19","doi-asserted-by":"publisher","first-page":"110245","DOI":"10.1016\/j.knosys.2022.110245","article-title":"Knowledge graph extension with a pre-trained language model via unified learning method","volume":"262","author":"Choi","year":"2023","journal-title":"Knowl.-Based Syst"},{"key":"B20","article-title":"Gap: A graph-aware language model framework for knowledge graph-to-text generation","author":"Colas","year":"2022","journal-title":"arXiv preprint arXiv:2204.06674"},{"key":"B21","article-title":"Knowledge neurons in pretrained transformers","author":"Dai","year":"2021","journal-title":"arXiv preprint arXiv:2104.08696"},{"key":"B22","article-title":"Chatel: entity linking with chatbots","author":"Ding","year":"2024","journal-title":"arXiv preprint arXiv:2402.14858"},{"key":"B23","doi-asserted-by":"publisher","first-page":"1877","DOI":"10.18653\/v1\/2024.naacl-long.104","article-title":"\u201cZRLLM: zero-shot relational learning on temporal knowledge graphs with large language models,\u201d","author":"Ding","year":"2024","journal-title":"Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)"},{"key":"B24","doi-asserted-by":"publisher","first-page":"147","DOI":"10.18653\/v1\/2024.acl-short.14","article-title":"\u201cBi-directional multi-granularity generation framework for knowledge graph-to-text with large language model,\u201d","author":"Du","year":"2024","journal-title":"Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers)"},{"key":"B25","article-title":"From local to global: A graph rag approach to query-focused summarization","author":"Edge","year":"2024","journal-title":"arXiv preprint arXiv:2404.16130"},{"key":"B26","volume-title":"Improving Data Quality: Consistency and Accuracy","author":"Fan","year":"2007"},{"key":"B27","article-title":"Knowledge solver: Teaching LLMs to search for domain knowledge from knowledge graphs","author":"Feng","year":"2023","journal-title":"arXiv preprint arXiv:2309.03118"},{"key":"B28","doi-asserted-by":"publisher","first-page":"413","DOI":"10.1145\/2488388.2488425","article-title":"\u201cAmie: association rule mining under incomplete evidence in ontological knowledge bases,\u201d","author":"Gal\u00e1rraga","year":"2013","journal-title":"Proceedings of the 22nd International Conference on World Wide Web"},{"key":"B29","article-title":"Llama-adapter v2: parameter-efficient visual instruction model","author":"Gao","year":"2023","journal-title":"arXiv preprint arXiv:2304.15010"},{"key":"B30","first-page":"408","article-title":"\u201cHow legal knowledge graph can help predict charges for legal text,\u201d","volume-title":"International Conference on Neural Information Processing","author":"Gao","year":"2023"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.401","article-title":"Two-stage generative question answering on temporal knowledge graph using large language models","author":"Gao","year":"2024","journal-title":"arXiv preprint arXiv:2402.16568.2402.16568"},{"key":"B32","doi-asserted-by":"crossref","first-page":"272","DOI":"10.1007\/978-3-319-93417-4_18","article-title":"\u201cEventkg: a multilingual event-centric temporal knowledge graph,\u201d","volume-title":"The Semantic Web: 15th International Conference, ESWC 2018, Heraklion, Crete, Greece, June 3\u20137, 2018, Proceedings 15","author":"Gottschalk","year":"2018"},{"key":"B33","doi-asserted-by":"publisher","first-page":"4497","DOI":"10.1145\/3627673.3680094","article-title":"\u201cCancerkg. org-a web-scale, interactive, verifiable knowledge graph-llm hybrid for assisting with optimal cancer treatment and care,\u201d","author":"Gubanov","year":"2024","journal-title":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management"},{"key":"B34","first-page":"140509","article-title":"\u201cMKGL: mastery of a three-word language,\u201d","author":"Guo","year":"2025","journal-title":"in Advances in Neural Information Processing Systems"},{"key":"B35","doi-asserted-by":"publisher","first-page":"8548","DOI":"10.1002\/int.22955","article-title":"A medical question answering system using large language models and knowledge graphs","volume":"37","author":"Guo","year":"2022","journal-title":"Int. J. Intell. Syst"},{"key":"B36","first-page":"3929","article-title":"\u201cRetrieval augmented language model pre-training,\u201d","volume-title":"International Conference on Machine Learning","author":"Guu","year":"2020"},{"key":"B37","article-title":"Bertnet: Harvesting knowledge graphs with arbitrary relations from pretrained language models","author":"Hao","year":"2022","journal-title":"arXiv preprint arXiv:2206.14268"},{"key":"B38","article-title":"Integrating graph contextualized knowledge into pre-trained language models","author":"He","year":"2019","journal-title":"arXiv preprint arXiv:1912.00147"},{"key":"B39","article-title":"How do scaling laws apply to knowledge graph engineering tasks? The impact of model size on large language model performance","author":"Heim","year":"2025","journal-title":"arXiv preprint arXiv:2505.16276"},{"key":"B40","article-title":"True: Re-evaluating factual consistency evaluation","author":"Honovich","year":"2022","journal-title":"arXiv preprint arXiv:2204.04991"},{"key":"B41","article-title":"Endowing language models with multimodal knowledge graph representations","author":"Huang","year":"2022","journal-title":"arXiv preprint arXiv:2206.13163"},{"key":"B42","doi-asserted-by":"publisher","first-page":"76","DOI":"10.1007\/s44163-024-00175-8","article-title":"A survey on augmenting knowledge graphs (kgs) with large language models (LLMS): models, evaluation metrics, benchmarks, and challenges","volume":"4","author":"Ibrahim","year":"2024","journal-title":"Disc. Artif. Intell"},{"key":"B43","first-page":"292","article-title":"\u201cEducational knowledge graph creation and augmentation via LLMS,\u201d","volume-title":"International Conference on Intelligent Tutoring Systems","author":"Jhajj","year":"2024"},{"key":"B44","article-title":"Structgpt: a general framework for large language model to reason over structured data","author":"Jiang","year":"2023","journal-title":"arXiv preprint arXiv:2305.09645"},{"key":"B45","article-title":"Kg-agent: an efficient autonomous agent framework for complex reasoning over knowledge graph","author":"Jiang","year":"2024","journal-title":"arXiv preprint arXiv:2402.11163"},{"key":"B46","article-title":"Text-augmented open knowledge graph completion via pre-trained language models","author":"Jiang","year":"2023","journal-title":"arXiv preprint arXiv:2305.15597"},{"key":"B47","first-page":"136220","article-title":"\u201cKg-fit: knowledge graph fine-tuning upon open-world knowledge,\u201d","author":"Jiang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B48","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1162\/tacl_a_00324","article-title":"How can we know what language models know?","volume":"8","author":"Jiang","year":"2020","journal-title":"Trans. Assoc. Comput. Linguist"},{"key":"B49","article-title":"Kala: knowledge-augmented language model adaptation","author":"Kang","year":"2022","journal-title":"arXiv preprint arXiv:2204.10555"},{"key":"B50","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3491209","article-title":"Trustworthy artificial intelligence: a review","volume":"55","author":"Kaur","year":"2022","journal-title":"ACM Comput. Surv"},{"key":"B51","article-title":"Jointgt: Graph-text joint representation learning for text generation from knowledge graphs","author":"Ke","year":"2021","journal-title":"arXiv preprint arXiv:2106.10502"},{"key":"B52","doi-asserted-by":"publisher","first-page":"1737","DOI":"10.18653\/v1\/2020.coling-main.153","article-title":"\u201cMulti-task learning for knowledge graph completion with pre-trained language models,\u201d","author":"Kim","year":"2020","journal-title":"Proceedings of the 28th International Conference on Computational Linguistics"},{"key":"B53","article-title":"Multimodal reasoning with multimodal knowledge graph","author":"Lee","year":"2024","journal-title":"arXiv preprint arXiv:2406.02030"},{"key":"B54","first-page":"9459","article-title":"\u201cRetrieval-augmented generation for knowledge-intensive nlp tasks,\u201d","author":"Lewis","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B55","article-title":"Dalk: dynamic co-augmentation of LLMs and kg to answer alzheimer's disease questions with scientific literature","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv:2405.04819"},{"key":"B56","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3627704","article-title":"Multi-task pre-training language model for semantic network completion","volume":"22","author":"Li","year":"2023","journal-title":"ACM Trans. Asian Low-Resour. Lang. Inf. Proc"},{"key":"B57","article-title":"A preliminary roadmap for LLMs as assistants in exploring, analyzing, and visualizing knowledge graphs","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv:2404.01425"},{"key":"B58","article-title":"Few-shot knowledge graph-to-text generation with pretrained language models","author":"Li","year":"2021","journal-title":"arXiv preprint arXiv:2106.01623"},{"key":"B59","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4608445","author":"Li","year":"2023","journal-title":"Findkg: dynamic knowledge graph with large language models for global finance"},{"key":"B60","article-title":"Ai transparency in the age of LLMs: A human-centered research roadmap","author":"Liao","year":"2023","journal-title":"arXiv preprint arXiv:2306.01941,01910"},{"key":"B61","article-title":"Gentkg: Generative forecasting on temporal knowledge graph with large language models","author":"Liao","year":"2023","journal-title":"arXiv preprint arXiv:2310.07793"},{"key":"B62","doi-asserted-by":"publisher","first-page":"4303","DOI":"10.18653\/v1\/2024.findings-naacl.268","article-title":"\u201cGentkg: generative forecasting on temporal knowledge graph with large language models,\u201d","author":"Liao","year":"2024","journal-title":"Findings of the Association for Computational Linguistics: NAACL 2024"},{"key":"B63","article-title":"Kagnet: Knowledge-aware graph networks for commonsense reasoning","author":"Lin","year":"2019","journal-title":"arXiv preprint arXiv:1909.02151"},{"key":"B64","first-page":"74","article-title":"\u201cRouge: a package for automatic evaluation of summaries,\u201d","author":"Lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"B65","doi-asserted-by":"crossref","first-page":"1192","DOI":"10.1109\/ICIPCA61593.2024.10709293","article-title":"\u201cDesign of legal judgment prediction on knowledge graph and deep learning,\u201d","volume-title":"2024 IEEE 2nd International Conference on Image Processing and Computer Applications (ICIPCA)","author":"Liu","year":"2024"},{"key":"B66","article-title":"Knowledge graph-enhanced large language models via path selection","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv:2406.13862"},{"key":"B67","doi-asserted-by":"publisher","first-page":"8759","DOI":"10.1609\/aaai.v38i8.28722","article-title":"\u201cTowards continual knowledge graph embedding via incremental distillation,\u201d","author":"Liu","year":"2024","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"B68","doi-asserted-by":"publisher","first-page":"1909","DOI":"10.1145\/3627673.3679793","article-title":"\u201cUnimel: a unified framework for multimodal entity linking with large language models,\u201d","author":"Liu","year":"2024","journal-title":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management"},{"key":"B69","article-title":"Spinach: Sparql-based information navigation for challenging real-world questions","author":"Liu","year":"2024","journal-title":"arXiv preprint arXiv:2407.11417"},{"key":"B70","doi-asserted-by":"publisher","first-page":"2901","DOI":"10.1609\/aaai.v34i03.5681","article-title":"\u201cK-bert: enabling language representation with knowledge graph,\u201d","author":"Liu","year":"2020","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"B71","first-page":"199","article-title":"\u201cFinetuning generative large language models with discrimination instructions for knowledge graph completion,\u201d","volume-title":"International Semantic Web Conference","author":"Liu","year":"2024"},{"key":"B72","doi-asserted-by":"crossref","first-page":"470","DOI":"10.1007\/978-3-030-30793-6_27","article-title":"\u201cPretrained transformers for simple question answering over knowledge graphs,\u201d","volume-title":"The Semantic Web-ISWC 2019: 18th International Semantic Web Conference, Auckland, New Zealand, October 26\u201330, 2019, Proceedings, Part I 18","author":"Lukovnikov","year":"2019"},{"key":"B73","article-title":"Chatkbqa: a generate-then-retrieve framework for knowledge base question answering with fine-tuned large language models","author":"Luo","year":"2023","journal-title":"arXiv preprint arXiv:2310.08975"},{"key":"B74","article-title":"Chatrule: mining logical rules with large language models for knowledge graph reasoning","author":"Luo","year":"","journal-title":"arXiv preprint arXiv:2309.01538"},{"key":"B75","article-title":"Reasoning on graphs: faithful and interpretable large language model reasoning","author":"Luo","year":"","journal-title":"arXiv preprint arXiv:2310.01061"},{"key":"B76","article-title":"Systematic assessment of factual knowledge in large language models","author":"Luo","year":"","journal-title":"arXiv preprint arXiv"},{"key":"B77","doi-asserted-by":"publisher","first-page":"124456","DOI":"10.1016\/j.eswa.2024.124456","article-title":"Factual consistency evaluation of summarization in the era of large language models","volume":"254","author":"Luo","year":"2024","journal-title":"Expert Syst. Appl"},{"key":"B78","doi-asserted-by":"publisher","first-page":"18751","DOI":"10.1609\/aaai.v38i17.29839","article-title":"\u201cStar: Boosting low-resource information extraction by structure-to-text data generation with large language models,\u201d","author":"Ma","year":"2024","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"B79","article-title":"Think-on-graph 2.0: deep and interpretable large language model reasoning with knowledge graph-guided retrieval","author":"Ma","year":"2024","journal-title":"arXiv e-prints, arXiv-2407"},{"key":"B80","article-title":"Dreeam: Guiding attention with evidence for improving document-level relation extraction","author":"Ma","year":"2023","journal-title":"arXiv preprint arXiv:2302.08675"},{"key":"B81","doi-asserted-by":"publisher","first-page":"2507","DOI":"10.1007\/s42835-022-01032-3","article-title":"Creating knowledge graph of electric power equipment faults based on bert-bilstm-crf model","volume":"17","author":"Meng","year":"2022","journal-title":"J. Electr. Eng. Technol"},{"key":"B82","article-title":"Rewire-then-probe: a contrastive recipe for probing biomedical knowledge of pre-trained language models","author":"Meng","year":"2021","journal-title":"arXiv preprint arXiv:2110.08173"},{"key":"B83","article-title":"Synergetic event understanding: a collaborative approach to cross-document event coreference resolution with large language models","author":"Min","year":"2024","journal-title":"arXiv preprint arXiv:2406.02148"},{"key":"B84","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1016\/j.ndteint.2003.09.005","article-title":"Optimal design of emat transmitters","volume":"37","author":"Mirkhani","year":"2004","journal-title":"NDT e Int"},{"key":"B85","article-title":"Skill: Structured knowledge infusion for large language models","author":"Moiseev","year":"2022","journal-title":"arXiv preprint arXiv:2205.08184"},{"key":"B86","first-page":"8097","article-title":"\u201cLeveraging LLMs few-shot learning to improve instruction-driven knowledge graph construction,\u201d","author":"Mou","year":"2024","journal-title":"Proceedings of the VLDB Endowment. ISSN 2150"},{"key":"B87","article-title":"Okay, let's do this! Modeling event coreference with generated rationales and knowledge distillation","author":"Nath","year":"2024","journal-title":"arXiv preprint arXiv:2404.03196"},{"key":"B88","article-title":"Large language models and knowledge graphs: opportunities and challenges","author":"Pan","year":"2023","journal-title":"arXiv preprint arXiv:2308.06374"},{"key":"B89","doi-asserted-by":"publisher","first-page":"3580","DOI":"10.1109\/TKDE.2024.3352100","article-title":"Unifying large language models and knowledge graphs: a roadmap","volume":"36","author":"Pan","year":"2024","journal-title":"IEEE Trans. Knowl. Data Eng"},{"key":"B90","doi-asserted-by":"publisher","first-page":"311","DOI":"10.3115\/1073083.1073135","article-title":"\u201cBleu: a method for automatic evaluation of machine translation,\u201d","author":"Papineni","year":"2002","journal-title":"Proceedings of the 40th annual meeting of the Association for Computational Linguistics"},{"key":"B91","doi-asserted-by":"publisher","first-page":"8160","DOI":"10.1109\/TII.2024.3366977","article-title":"Joint knowledge graph and large language model for fault diagnosis and its application in aviation assembly","volume":"20","author":"Peifeng","year":"2024","journal-title":"IEEE Trans. Ind. Inform"},{"key":"B92","article-title":"Graph retrieval-augmented generation: a survey","author":"Peng","year":"2024","journal-title":"arXiv preprint arXiv:2408.08921"},{"key":"B93","article-title":"Language models as knowledge bases?","author":"Petroni","year":"2019","journal-title":"arXiv preprint arXiv:1909.01066"},{"key":"B94","article-title":"Convkgyarn: Spinning configurable and scalable conversational knowledge graph qa datasets with large language models","author":"Pradeep","year":"2024","journal-title":"arXiv preprint arXiv:2408.05948"},{"key":"B95","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/MASSP.1986.1165342","article-title":"An introduction to hidden markov models","volume":"3","author":"Rabiner","year":"1986","journal-title":"IEEE Assp Magaz"},{"key":"B96","doi-asserted-by":"publisher","first-page":"127974","DOI":"10.1109\/ACCESS.2023.3331585","article-title":"Improving fmea comprehensibility via common-sense knowledge graph completion techniques","volume":"11","author":"Razouk","year":"2023","journal-title":"IEEE Access"},{"key":"B97","doi-asserted-by":"publisher","first-page":"6616","DOI":"10.1145\/3637528.3671460","article-title":"\u201cA survey of large language models for graphs,\u201d","author":"Ren","year":"2024","journal-title":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining"},{"key":"B98","article-title":"LKPNR: LLM and kg for personalized news recommendation framework","author":"Runfeng","year":"2023","journal-title":"arXiv preprint arXiv:2308.12028"},{"key":"B99","article-title":"KG-RAG: bridging the gap between knowledge and creativity","author":"Sanmartin","year":"2024","journal-title":"arXiv preprint arXiv:2405.12035"},{"key":"B100","article-title":"Grapheval: a knowledge-graph based llm hallucination evaluation framework","author":"Sansford","year":"2024","journal-title":"arXiv preprint arXiv:2407.10793"},{"key":"B101","article-title":"Language models are greedy reasoners: a systematic formal analysis of chain-of-thought","author":"Saparov","year":"2022","journal-title":"arXiv preprint arXiv:2210.01240"},{"key":"B102","article-title":"Sequence-to-sequence knowledge graph completion and question answering","author":"Saxena","year":"2022","journal-title":"arXiv preprint arXiv:2203.10321"},{"key":"B103","article-title":"Joint language semantic and structure embedding for knowledge graph completion","author":"Shen","year":"2022","journal-title":"arXiv preprint arXiv:2209.08721"},{"key":"B104","doi-asserted-by":"publisher","first-page":"2556","DOI":"10.1109\/TKDE.2021.3117715","article-title":"Entity linking meets deep learning: Techniques and solutions","volume":"35","author":"Shen","year":"2021","journal-title":"IEEE Trans. Knowl. Data Eng"},{"key":"B105","doi-asserted-by":"publisher","first-page":"132306","DOI":"10.1016\/j.physd.2019.132306","article-title":"Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network","volume":"404","author":"Sherstinsky","year":"2020","journal-title":"Physica D"},{"key":"B106","first-page":"175","article-title":"\u201cLEGAL-LM: knowledge graph enhanced large language models for law consulting,\u201d","volume-title":"International Conference on Intelligent Computing","author":"Shi","year":"2024"},{"key":"B107","article-title":"Autoprompt: eliciting knowledge from language models with automatically generated prompts","author":"Shin","year":"2020","journal-title":"arXiv preprint arXiv:2010.15980"},{"key":"B108","article-title":"Knowledge graph large language model (KG-LLM) for link prediction","author":"Shu","year":"2024","journal-title":"arXiv preprint arXiv:2403.07311"},{"key":"B109","doi-asserted-by":"crossref","first-page":"203","DOI":"10.18653\/v1\/D19-5827","article-title":"\u201cGeneralizing question answering system with pre-trained language model fine-tuning,\u201d","author":"Su","year":"2019","journal-title":"Proceedings of the 2nd Workshop on Machine Reading for Question Answering"},{"key":"B110","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1016\/j.aiopen.2021.06.004","article-title":"Cokebert: contextual knowledge selection and embedding towards enhanced pre-trained language models","volume":"2","author":"Su","year":"2021","journal-title":"AI Open"},{"key":"B111","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3597503.3639157","article-title":"\u201cEnhancing exploratory testing by large language model and knowledge graph,\u201d","author":"Su","year":"2024","journal-title":"Proceedings of the IEEE\/ACM 46th International Conference on Software Engineering"},{"key":"B112","doi-asserted-by":"publisher","first-page":"6533","DOI":"10.1609\/aaai.v37i5.25803","article-title":"\u201cMulti-aspect explainable inductive relation prediction by sentence transformer,\u201d","author":"Su","year":"2023","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"B113","article-title":"Think-on-graph: deep and responsible reasoning of large language model on knowledge graph","author":"Sun","year":"2023","journal-title":"arXiv preprint arXiv:2307.07697"},{"key":"B114","doi-asserted-by":"publisher","first-page":"128726","DOI":"10.1016\/j.neucom.2024.128726","article-title":"SF-GPT: a training-free method to enhance capabilities for knowledge graph construction in LLMs","volume":"613","author":"Sun","year":"2025","journal-title":"Neurocomputing"},{"key":"B115","article-title":"Colake: contextualized language and knowledge embedding","author":"Sun","year":"2020","journal-title":"arXiv preprint arXiv:2010.00309"},{"key":"B116","article-title":"Jointlk: joint reasoning with language models and knowledge graphs for commonsense question answering","author":"Sun","year":"","journal-title":"arXiv preprint arXiv:2112.02732"},{"key":"B117","article-title":"Ernie 3.0: Large-scale knowledge enhanced pre-training for language understanding and generation","author":"Sun","year":"","journal-title":"arXiv preprint arXiv:2107.02137"},{"key":"B118","article-title":"Can language models be biomedical knowledge bases?","author":"Sung","year":"2021","journal-title":"arXiv preprint arXiv:2109.07154"},{"key":"B119","article-title":"Evit: Event-oriented instruction tuning for event reasoning","author":"Tao","year":"2024","journal-title":"arXiv preprint arXiv:2404.11978"},{"key":"B120","doi-asserted-by":"publisher","first-page":"19080","DOI":"10.1609\/aaai.v38i17.29875","article-title":"\u201cGraph neural prompting with large language models,\u201d","author":"Tian","year":"2024","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"B121","doi-asserted-by":"publisher","first-page":"102535","DOI":"10.1016\/j.artmed.2023.102535","article-title":"Knowledge graph assisted end-to-end medical dialog generation","volume":"139","author":"Varshney","year":"2023","journal-title":"Artif. Intell. Med"},{"key":"B122","article-title":"\u201cAttention is all you need,\u201d","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"B123","doi-asserted-by":"publisher","first-page":"e56532","DOI":"10.2196\/56532","article-title":"The accuracy and capability of artificial intelligence solutions in health care examinations and certificates: systematic review and meta-analysis","volume":"26","author":"Waldock","year":"2024","journal-title":"J. Med. Internet Res"},{"key":"B124","doi-asserted-by":"publisher","first-page":"1737","DOI":"10.1145\/3442381.3450043","article-title":"\u201cStructure-augmented text representation learning for efficient knowledge graph completion,\u201d","author":"Wang","year":"2021","journal-title":"Proceedings of the Web Conference 2021"},{"key":"B125","doi-asserted-by":"publisher","first-page":"s1115","DOI":"10.1007\/s10115-025-02399-1","article-title":"Llm-kgmqa: Large language model-augmented multi-hop question-answering system based on knowledge graph in medical field","volume":"2025","author":"Wang","year":"2024","journal-title":"Knowl. Inf. Syst"},{"key":"B126","article-title":"Knowledge prompting in pre-trained language model for natural language understanding","author":"Wang","year":"2022","journal-title":"arXiv preprint arXiv:2210.08536"},{"key":"B127","article-title":"Boosting language models reasoning with chain-of-knowledge prompting","author":"Wang","year":"","journal-title":"arXiv preprint arXiv:2306.06427"},{"key":"B128","article-title":"A survey on temporal knowledge graph completion: Taxonomy, progress, and prospects","author":"Wang","year":"","journal-title":"arXiv preprint arXiv:2308.02457"},{"key":"B129","article-title":"Knowledge-driven cot: Exploring faithful reasoning in LLMs for knowledge-intensive question answering","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv:2308.13259"},{"key":"B130","article-title":"Llm as prompter: low-resource inductive reasoning on arbitrary knowledge graphs","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv:2402.11804"},{"key":"B131","article-title":"SIMKGC: simple contrastive knowledge graph completion with pre-trained language models","author":"Wang","year":"2022","journal-title":"arXiv preprint arXiv:2203.02167"},{"key":"B132","first-page":"111","article-title":"\u201cReasoning through memorization: Nearest neighbor knowledge graph embeddings,\u201d","volume-title":"CCF International Conference on Natural Language Processing and Chinese Computing","author":"Wang","year":"2023"},{"key":"B133","article-title":"GPT-ner: named entity recognition via large language models","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv:2304.10428"},{"key":"B134","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1162\/tacl_a_00360","article-title":"Kepler: a unified model for knowledge embedding and pre-trained language representation","volume":"9","author":"Wang","year":"2021","journal-title":"Trans. Assoc. Comput. Linguist"},{"key":"B135","article-title":"Language models as knowledge embeddings","author":"Wang","year":"2022","journal-title":"arXiv preprint arXiv:2206.12617"},{"key":"B136","article-title":"Resolving knowledge conflicts in large language models","author":"Wang","year":"2023","journal-title":"arXiv preprint arXiv:2310.00935"},{"key":"B137","article-title":"Kc-genre: a knowledge-constrained generative re-ranking method based on large language models for knowledge graph completion","author":"Wang","year":"2024","journal-title":"arXiv preprint arXiv:2403.17532"},{"key":"B138","article-title":"Mindmap: knowledge graph prompting sparks graph of thoughts in large language models","author":"Wen","year":"2023","journal-title":"arXiv preprint arXiv:2308.09729"},{"key":"B139","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1145\/3487553.3524238","article-title":"\u201cFrom discrimination to generation: Knowledge graph completion with generative transformer,\u201d","author":"Xie","year":"2022","journal-title":"Companion Proceedings of the Web Conference 2022"},{"key":"B140","article-title":"LLMAEL: Large language models are good context augmenters for entity linking","author":"Xin","year":"2024","journal-title":"arXiv:2407.04020"},{"key":"B141","article-title":"Large language models can learn temporal reasoning","author":"Xiong","year":"2024","journal-title":"arXiv preprint arXiv:2401.06853"},{"key":"B142","article-title":"Pretrained encyclopedia: weakly supervised knowledge-pretrained language model","author":"Xiong","year":"2019","journal-title":"arXiv preprint arXiv:1912.09637"},{"key":"B143","article-title":"Pre-trained language model with prompts for temporal knowledge graph completion","author":"Xu","year":"2023","journal-title":"arXiv preprint arXiv:2305.07912"},{"key":"B144","article-title":"Generate-on-graph: treat llm as both agent and kg in incomplete knowledge graph question answering","author":"Xu","year":"2024","journal-title":"arXiv preprint arXiv:2404.14741"},{"key":"B145","doi-asserted-by":"publisher","first-page":"3091","DOI":"10.1109\/TKDE.2024.3360454","article-title":"Give us the facts: enhancing large language models with knowledge graphs for fact-aware language modeling","volume":"36","author":"Yang","year":"","journal-title":"IEEE Trans. Knowl. Data Eng"},{"key":"B146","article-title":"Two heads are better than one: Integrating knowledge from knowledge graphs and large language models for entity alignment","author":"Yang","year":"","journal-title":"arXiv preprint arXiv:2401.16960"},{"key":"B147","article-title":"Kg-rank: Enhancing large language models for medical qa with knowledge graphs and ranking techniques","author":"Yang","year":"","journal-title":"arXiv preprint arXiv:2403.05881"},{"key":"B148","article-title":"Graphusion: Leveraging large language models for scientific knowledge graph fusion and construction in nlp education","author":"Yang","year":"","journal-title":"arXiv preprint arXiv:2407.10794"},{"key":"B149","article-title":"Kg-bert: bert for knowledge graph completion","author":"Yao","year":"2019","journal-title":"arXiv preprint arXiv:1909.03193"},{"key":"B150","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.45","article-title":"Qa-gnn: Reasoning with language models and knowledge graphs for question answering","author":"Yasunaga","year":"2021","journal-title":"arXiv preprint arXiv:2104.06378"},{"key":"B151","doi-asserted-by":"publisher","first-page":"778","DOI":"10.1145\/3485447.3511921","article-title":"\u201cOntology-enhanced prompt-tuning for few-shot learning,\u201d","author":"Ye","year":"2022","journal-title":"Proceedings of the ACM Web Conference 2022"},{"key":"B152","doi-asserted-by":"publisher","first-page":"62","DOI":"10.13209\/j.0479-8023.2023.073","article-title":"Interpretable biomedical reasoning via deep fusion of knowledge graph and pre-trained language models","volume":"60","author":"Yinxin","year":"2024","journal-title":"Beijing Da Xue Xue Bao"},{"key":"B153","article-title":"Kglm: Integrating knowledge graph structure in language models for link prediction","author":"Youn","year":"2022","journal-title":"arXiv preprint arXiv:2211.02744"},{"key":"B154","doi-asserted-by":"publisher","first-page":"11630","DOI":"10.1609\/aaai.v36i10.21417","article-title":"\u201cJaket: joint pre-training of knowledge graph and language understanding,\u201d","author":"Yu","year":"2022","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"B155","article-title":"Agenttuning: enabling generalized agent abilities for LLMs","author":"Zeng","year":"2023","journal-title":"arXiv preprint arXiv:2310.12823"},{"key":"B156","doi-asserted-by":"publisher","first-page":"5923","DOI":"10.1609\/aaai.v36i5.20537","article-title":"\u201cInductive relation prediction by bert,\u201d","author":"Zha","year":"2022","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"B157","article-title":"E-bert: a phrase and product knowledge enhanced language model for e-commerce","author":"Zhang","year":"2020","journal-title":"arXiv preprint arXiv:2009.02835"},{"key":"B158","doi-asserted-by":"publisher","first-page":"5123","DOI":"10.18653\/v1\/2022.emnlp-main.342","article-title":"\u201cDrlk: dynamic hierarchical reasoning with language model and knowledge graph for question answering,\u201d","author":"Zhang","year":"2022","journal-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing"},{"key":"B159","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s41060-024-00661-3","article-title":"Knowledge graph accuracy evaluation: an llm-enhanced embedding approach","volume":"2024","author":"Zhang","year":"2024","journal-title":"Int. J. Data Sci. Anal"},{"key":"B160","doi-asserted-by":"publisher","first-page":"2357","DOI":"10.1109\/TKDE.2023.3325484","article-title":"Autoalign: fully automatic and effective knowledge graph alignment enabled by large language models","volume":"36","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Knowl. Data Eng"},{"key":"B161","doi-asserted-by":"publisher","first-page":"11703","DOI":"10.1609\/aaai.v36i10.21425","article-title":"\u201cDKPLM: decomposable knowledge-enhanced pre-trained language model for natural language understanding,\u201d","author":"Zhang","year":"2022","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"B162","article-title":"Greaselm: graph reasoning enhanced language models for question answering","author":"Zhang","year":"2022","journal-title":"arXiv preprint arXiv:2201.08860"},{"key":"B163","article-title":"Making large language models perform better in knowledge graph completion","author":"Zhang","year":"2023","journal-title":"arXiv preprint arXiv:2310.06671"},{"key":"B164","article-title":"Ernie: enhanced language representation with informative entities","author":"Zhang","year":"2019","journal-title":"arXiv preprint arXiv:1905.07129"},{"key":"B165","doi-asserted-by":"publisher","first-page":"1595","DOI":"10.18653\/v1\/2024.emnlp-main.95","article-title":"\u201cCross-domain ner with generated task-oriented knowledge: an empirical study from information density perspective,\u201d","author":"Zhang","year":"","journal-title":"Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing"},{"key":"B166","doi-asserted-by":"publisher","first-page":"259","DOI":"10.18653\/v1\/2020.findings-emnlp.25","article-title":"\u201cPretrain-kge: learning knowledge representation from pretrained language models,\u201d","author":"Zhang","year":"2020","journal-title":"Findings of the Association for Computational Linguistics: EMNLP 2020"},{"key":"B167","article-title":"Llm hallucinations in practical code generation: Phenomena, mechanism, and mitigation","author":"Zhang","year":"","journal-title":"arXiv preprint arXiv:2409.20550"},{"key":"B168","first-page":"6642","article-title":"\u201cKg-cot: chain-of-thought prompting of large language models over knowledge graphs for knowledge-aware question answering,\u201d","volume-title":"Proceedings of the Thirty-Third International Joint Conference on Artificial Intelligence (IJCAI-24)","author":"Zhao","year":"2024"},{"key":"B169","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1109\/ICDE60146.2024.00013","article-title":"\u201cKnowledge graph enhanced multimodal transformer for image-text retrieval,\u201d","volume-title":"2024 IEEE 40th International Conference on Data Engineering (ICDE)","author":"Zheng","year":"2024"},{"key":"B170","doi-asserted-by":"publisher","first-page":"8576","DOI":"10.1145\/3664647.3680966","article-title":"\u201cSelf-adaptive fine-grained multi-modal data augmentation for semi-supervised muti-modal coreference resolution,\u201d","author":"Zheng","year":"2024","journal-title":"Proceedings of the 32nd ACM International Conference on Multimedia"},{"key":"B171","doi-asserted-by":"publisher","first-page":"102333","DOI":"10.1016\/j.aei.2023.102333","article-title":"Causalkgpt: industrial structure causal knowledge-enhanced large language model for cause analysis of quality problems in aerospace product manufacturing","volume":"59","author":"Zhou","year":"2024","journal-title":"Adv. Eng. Inform"},{"key":"B172","doi-asserted-by":"publisher","first-page":"119369","DOI":"10.1016\/j.eswa.2022.119369","article-title":"Pre-training language model incorporating domain-specific heterogeneous knowledge into a unified representation","volume":"215","author":"Zhu","year":"2023","journal-title":"Expert Syst. Appl"}],"container-title":["Frontiers in Computer Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcomp.2025.1590632\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,16]],"date-time":"2025-07-16T05:37:35Z","timestamp":1752644255000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcomp.2025.1590632\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,16]]},"references-count":172,"alternative-id":["10.3389\/fcomp.2025.1590632"],"URL":"https:\/\/doi.org\/10.3389\/fcomp.2025.1590632","relation":{},"ISSN":["2624-9898"],"issn-type":[{"value":"2624-9898","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,16]]},"article-number":"1590632"}}