{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T16:08:30Z","timestamp":1780330110106,"version":"3.54.1"},"reference-count":48,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2027,1,1]],"date-time":"2027-01-01T00:00:00Z","timestamp":1798761600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Standards & Interfaces"],"published-print":{"date-parts":[[2027,1]]},"DOI":"10.1016\/j.csi.2026.104179","type":"journal-article","created":{"date-parts":[[2026,5,27]],"date-time":"2026-05-27T23:45:11Z","timestamp":1779925511000},"page":"104179","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Graph\u2013language synergy in intelligent information systems: A systems-level review of GNN\u2013LLM integration, GraphRAG, and knowledge-grounded reasoning"],"prefix":"10.1016","volume":"99","author":[{"given":"Arash","family":"Salehpour","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8314-9051","authenticated-orcid":false,"given":"Alireza","family":"Souri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sisi","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kuanching","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.csi.2026.104179_bib0001","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.130776","article-title":"Search to integrate multi-level heuristics with graph neural networks for multi-relational link prediction","volume":"649","author":"Wu","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.csi.2026.104179_bib0002","series-title":"Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining","article-title":"Struct-x: enhancing the reasoning capabilities of large language models in structured data scenarios","volume":"1","author":"Tan","year":"2025"},{"issue":"12","key":"10.1016\/j.csi.2026.104179_bib0003","doi-asserted-by":"crossref","first-page":"8622","DOI":"10.1109\/TKDE.2024.3469578","article-title":"Large language models on graphs: a comprehensive survey","volume":"36","author":"Jin","year":"2024","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.csi.2026.104179_bib0004","unstructured":"H. Yang, et al., Gl-fusion: rethinking the combination of graph neural network and large language model. arXiv preprint arXiv:2412.06849, 2024."},{"issue":"15","key":"10.1016\/j.csi.2026.104179_bib0005","doi-asserted-by":"crossref","first-page":"25648","DOI":"10.1109\/JIOT.2024.3379363","article-title":"TrustBCFL: mitigating data bias in IoT through blockchain-enabled federated learning","volume":"11","author":"Zhou","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.csi.2026.104179_bib0006","article-title":"Trusthfl: an efficient aggregation method for trustworthy hierarchical federated learning","author":"Zhou","year":"2026","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.csi.2026.104179_bib0007","first-page":"1","article-title":"MultiSecDFL: multi-metric filtering-based secure aggregation method for decentralized federated learning","author":"Zhou","year":"2026","journal-title":"IEEE Trans. Consum. Electron."},{"key":"10.1016\/j.csi.2026.104179_bib0008","article-title":"ACM transactions on intelligent systems and technology","author":"Wang","year":"2011","journal-title":"ACM Trans. Intell. Syst. Technol."},{"issue":"6","key":"10.1016\/j.csi.2026.104179_bib0009","doi-asserted-by":"crossref","first-page":"1011","DOI":"10.1007\/s11633-024-1510-8","article-title":"A comprehensive survey on trustworthy graph neural networks: privacy, robustness, fairness, and explainability","volume":"21","author":"Dai","year":"2024","journal-title":"Mach. Intell. Res."},{"key":"10.1016\/j.csi.2026.104179_bib0010","article-title":"Graph foundation models: concepts, opportunities and challenges","author":"Liu","year":"2025","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.csi.2026.104179_bib0011","series-title":"Semantic Contextual Embedding For Domain-Specific Task Transfer in Large Language Models","author":"Nesbitt","year":"2024"},{"key":"10.1016\/j.csi.2026.104179_bib0012","unstructured":"L. Luo, et al., Graph-constrained reasoning: faithful reasoning on knowledge graphs with large language models. arXiv preprint arXiv:2410.13080, 2024."},{"issue":"11","key":"10.1016\/j.csi.2026.104179_bib0013","doi-asserted-by":"crossref","DOI":"10.1007\/s11704-025-50472-3","article-title":"Large language models meet nlp: a survey","volume":"20","author":"Qin","year":"2026","journal-title":"Front. Comput. Sci."},{"issue":"6","key":"10.1016\/j.csi.2026.104179_bib0014","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1007\/s00607-025-01499-8","article-title":"A review on synergizing knowledge graphs and large language models","volume":"107","author":"Yang","year":"2025","journal-title":"Computing"},{"key":"10.1016\/j.csi.2026.104179_bib0015","article-title":"FedAHPIP: federated learning with adaptive hot parameter identification and personalized anchoring for multi-agent collaboration","volume":"51","author":"Liang","year":"2026","journal-title":"J. Ind. Inf. Integr."},{"key":"10.1016\/j.csi.2026.104179_bib0016","doi-asserted-by":"crossref","unstructured":"C. Mavromatis and G. Karypis, Gnn-rag: graph neural retrieval for large language model reasoning. arXiv preprint arXiv:2405.20139, 2024.","DOI":"10.18653\/v1\/2025.findings-acl.856"},{"issue":"5","key":"10.1016\/j.csi.2026.104179_bib0017","doi-asserted-by":"crossref","first-page":"1969","DOI":"10.1109\/TITS.2014.2308540","article-title":"Task-specific performance evaluation of UGVs: case studies at the IVFC","volume":"15","author":"Huang","year":"2014","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"10.1016\/j.csi.2026.104179_bib0018","series-title":"Proceedings of the AAAI Conference On Artificial Intelligence","article-title":"Graph neural prompting with large language models","author":"Tian","year":"2024"},{"key":"10.1016\/j.csi.2026.104179_bib0019","unstructured":"Z. Chen, et al., Label-free node classification on graphs with large language models (LLMS). arXiv preprint arXiv:2310.04668, 2023."},{"key":"10.1016\/j.csi.2026.104179_bib0020","unstructured":"X. Wu, et al., When do LLMS help with node classification? a comprehensive analysis. arXiv preprint arXiv:2502.00829, 2025."},{"key":"10.1016\/j.csi.2026.104179_bib0021","unstructured":"L. Kong, et al., Gofa: a generative one-for-all model for joint graph language modeling. arXiv preprint arXiv:2407.09709, 2024."},{"key":"10.1016\/j.csi.2026.104179_bib0022","first-page":"29948","article-title":"Ragraph: a general retrieval-augmented graph learning framework","volume":"37","author":"Jiang","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.csi.2026.104179_bib0023","series-title":"Proceedings of the ACM Web Conference","article-title":"RAG-GFM: overcoming In-memory bottlenecks in graph foundation models via retrieval-augmented generation","author":"Yuan","year":"2026"},{"key":"10.1016\/j.csi.2026.104179_bib0024","unstructured":"H.Q. Yu and F. McQuade, Rag-kg-il: a multi-agent hybrid framework for reducing hallucinations and enhancing LLM reasoning through rag and incremental knowledge graph learning integration. arXiv preprint arXiv:2503.13514, 2025."},{"key":"10.1016\/j.csi.2026.104179_bib0025","unstructured":"Z. Chen, et al., Knowledge graphs meet multi-modal learning: a comprehensive survey. arXiv preprint arXiv:2402.05391, 2024."},{"key":"10.1016\/j.csi.2026.104179_bib0026","unstructured":"H. Bian, LLM-empowered knowledge graph construction: a survey. arXiv preprint arXiv:2510.20345, 2025."},{"key":"10.1016\/j.csi.2026.104179_bib0027","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","article-title":"Aligning vision to language: annotation-free multimodal knowledge graph construction for enhanced LLMS reasoning","author":"Liu","year":"2025"},{"key":"10.1016\/j.csi.2026.104179_bib0028","series-title":"Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining","article-title":"A survey of large language models for graphs","author":"Ren","year":"2024"},{"key":"10.1016\/j.csi.2026.104179_bib0029","unstructured":"Y. Li, et al., A survey of graph meets large language model: progress and future directions. arXiv preprint arXiv:2311.12399, 2023."},{"issue":"2","key":"10.1016\/j.csi.2026.104179_bib0030","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3777378","article-title":"Graph retrieval-augmented generation: a survey","volume":"44","author":"Peng","year":"2026","journal-title":"ACM Trans. Inf. Syst."},{"key":"10.1016\/j.csi.2026.104179_bib0031","unstructured":"Q. Zhang, et al., A survey of graph retrieval-augmented generation for customized large language models. arXiv preprint arXiv:2501.13958, 2025."},{"issue":"7","key":"10.1016\/j.csi.2026.104179_bib0032","doi-asserted-by":"crossref","first-page":"1147","DOI":"10.3390\/math13071147","article-title":"Large language models meet graph neural networks: a perspective of graph mining","volume":"13","author":"You","year":"2025","journal-title":"Mathematics"},{"key":"10.1016\/j.csi.2026.104179_bib0033","series-title":"Proceedings of the AAAI Conference On Artificial Intelligence","article-title":"Jaket: joint pre-training of knowledge graph and language understanding","author":"Yu","year":"2022"},{"issue":"1","key":"10.1016\/j.csi.2026.104179_bib0034","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1109\/MIS.2023.3332242","article-title":"Integrating graphs with large language models: methods and prospects","volume":"39","author":"Pan","year":"2024","journal-title":"IEEE Intell. Syst."},{"issue":"9","key":"10.1016\/j.csi.2026.104179_bib0035","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3686806","article-title":"Neural-symbolic methods for knowledge graph reasoning: a survey","volume":"18","author":"Cheng","year":"2024","journal-title":"ACM Trans. Knowl. Discov. Data"},{"key":"10.1016\/j.csi.2026.104179_bib0036","unstructured":"A. Tikna, Task and motion planning in neuro-symbolic robotics: from individual agents to multi-agent systems. 2026."},{"key":"10.1016\/j.csi.2026.104179_bib0037","unstructured":"B.P. Allen, L. Stork, and P. Groth, Knowledge engineering using large language models. arXiv preprint arXiv:2310.00637, 2023."},{"key":"10.1016\/j.csi.2026.104179_bib0038","doi-asserted-by":"crossref","unstructured":"Y. Cao, et al., Lego-graphrag: modularizing graph-based retrieval-augmented generation for design space exploration. arXiv preprint arXiv:2411.05844, 2024.","DOI":"10.14778\/3748191.3748194"},{"key":"10.1016\/j.csi.2026.104179_bib0039","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113236","article-title":"AMS: a hyperspectral image classification method based on SVM and multi-modal attention network","volume":"314","author":"Chen","year":"2025","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.csi.2026.104179_bib0040","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2022.110030","article-title":"Anomal-E: a self-supervised network intrusion detection system based on graph neural networks","volume":"258","author":"Caville","year":"2022","journal-title":"Knowl. Based Syst."},{"issue":"1","key":"10.1016\/j.csi.2026.104179_bib0041","doi-asserted-by":"crossref","first-page":"684","DOI":"10.1109\/TNSM.2022.3213807","article-title":"Flow topology-based graph convolutional network for intrusion detection in label-limited IoT networks","volume":"20","author":"Deng","year":"2022","journal-title":"IEEE Trans. Netw. Serv. Manag."},{"key":"10.1016\/j.csi.2026.104179_bib0042","article-title":"Enhancing network security using knowledge graphs and large language models for explainable threat detection","author":"Belcastro","year":"2025","journal-title":"Future Gener. Comput. Syst."},{"issue":"3","key":"10.1016\/j.csi.2026.104179_bib0043","doi-asserted-by":"crossref","first-page":"626","DOI":"10.1007\/s10618-014-0365-y","article-title":"Graph based anomaly detection and description: a survey","volume":"29","author":"Akoglu","year":"2015","journal-title":"Data Min. Knowl. Discov."},{"issue":"27\u201328","key":"10.1016\/j.csi.2026.104179_bib0044","article-title":"A systematic review of graph\u2010based representation techniques for cyber\u2010attack detection across application domains","volume":"37","author":"Kanca","year":"2025","journal-title":"Concurr. Comput. Pract. Exp."},{"key":"10.1016\/j.csi.2026.104179_bib0045","unstructured":"Y. Shen, et al., GraphextQA: a benchmark for evaluating graph-enhanced large language models. arXiv preprint arXiv:2310.08487, 2023."},{"key":"10.1016\/j.csi.2026.104179_bib0046","first-page":"127129","article-title":"Stark: benchmarking LLM retrieval on textual and relational knowledge bases","volume":"37","author":"Wu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.csi.2026.104179_bib0047","doi-asserted-by":"crossref","unstructured":"Z. Liu, et al., SKA-bench: a fine-grained benchmark for evaluating structured knowledge understanding of LLMs. arXiv preprint arXiv:2507.17178, 2025.","DOI":"10.18653\/v1\/2025.findings-emnlp.194"},{"key":"10.1016\/j.csi.2026.104179_bib0048","article-title":"A comprehensive survey of dynamic graph neural networks: models, frameworks, benchmarks, experiments and challenges","author":"Feng","year":"2025","journal-title":"IEEE Trans. Knowl. Data Eng."}],"container-title":["Computer Standards & Interfaces"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S092054892600053X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S092054892600053X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T15:56:29Z","timestamp":1780329389000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S092054892600053X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2027,1]]},"references-count":48,"alternative-id":["S092054892600053X"],"URL":"https:\/\/doi.org\/10.1016\/j.csi.2026.104179","relation":{},"ISSN":["0920-5489"],"issn-type":[{"value":"0920-5489","type":"print"}],"subject":[],"published":{"date-parts":[[2027,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Graph\u2013language synergy in intelligent information systems: A systems-level review of GNN\u2013LLM integration, GraphRAG, and knowledge-grounded reasoning","name":"articletitle","label":"Article Title"},{"value":"Computer Standards & Interfaces","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.csi.2026.104179","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104179"}}