{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T12:14:24Z","timestamp":1780402464942,"version":"3.54.1"},"reference-count":72,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,5,29]],"date-time":"2026-05-29T00:00:00Z","timestamp":1780012800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neural Networks"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.neunet.2026.109162","type":"journal-article","created":{"date-parts":[[2026,5,24]],"date-time":"2026-05-24T00:38:13Z","timestamp":1779583093000},"page":"109162","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Enhance graph alignment for large language models"],"prefix":"10.1016","volume":"203","author":[{"given":"Haitong","family":"Luo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0095-4811","authenticated-orcid":false,"given":"Xuying","family":"Meng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Suhang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianxiang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fali","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yujun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neunet.2026.109162_bib0001","series-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"10.1016\/j.neunet.2026.109162_bib0002","series-title":"Proceedings of the 17th ACM conference on recommender systems","first-page":"1007","article-title":"Tallrec: An effective and efficient tuning framework to align large language model with recommendation","author":"Bao","year":"2023"},{"issue":"1","key":"10.1016\/j.neunet.2026.109162_bib0003","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1016\/j.omega.2004.03.007","article-title":"A novel representation of graph structures in web mining and data analysis","volume":"33","author":"B\u0142a\u017cewicz","year":"2005","journal-title":"Omega"},{"key":"10.1016\/j.neunet.2026.109162_bib0004","series-title":"Llaga: Large language and graph assistant","author":"Chen","year":"2024"},{"issue":"2","key":"10.1016\/j.neunet.2026.109162_bib0005","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1145\/3655103.3655110","article-title":"Exploring the potential of large language models (LLMs) in learning on graphs","volume":"25","author":"Chen","year":"2024","journal-title":"ACM SIGKDD Explorations Newsletter"},{"key":"10.1016\/j.neunet.2026.109162_bib0006","series-title":"Label-free node classification on graphs with large language models (llms)","author":"Chen","year":"2023"},{"key":"10.1016\/j.neunet.2026.109162_bib0007","unstructured":"Chiang, W.-L., Li, Z., Lin, Z., Sheng, Y., Wu, Z., Zhang, H., Zheng, L., Zhuang, S., Zhuang, Y., Gonzalez, J. E. et al. (2023). Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality. (accessed 14 April 2023), 2(3), 6. See https:\/\/vicuna.lmsys.org."},{"key":"10.1016\/j.neunet.2026.109162_bib0008","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","volume":"29","author":"Defferrard","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109162_bib0009","first-page":"4171","article-title":"Pre-training of deep bidirectional transformers for language understanding in: Proceedings of the 2019 conference of the north american chapter of the association for computational linguistics: Human language technologies, volume 1 (long and short papers)","author":"Devlin","year":"2019","journal-title":"Minneapolis, MN: Association for Computational Linguistics"},{"issue":"8","key":"10.1016\/j.neunet.2026.109162_bib0010","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3669906","article-title":"Anomaly detection in dynamic graphs: A comprehensive survey","volume":"18","author":"Ekle","year":"2024","journal-title":"ACM Transactions on Knowledge Discovery from Data"},{"key":"10.1016\/j.neunet.2026.109162_bib0011","series-title":"Talk like a graph: Encoding graphs for large language models","author":"Fatemi","year":"2023"},{"key":"10.1016\/j.neunet.2026.109162_bib0012","series-title":"Icassp 2024-2024 IEEE international conference on acoustics, speech and signal processing (Icassp)","first-page":"13351","article-title":"Prompting large language models with speech recognition abilities","author":"Fathullah","year":"2024"},{"key":"10.1016\/j.neunet.2026.109162_bib0013","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.107777","article-title":"Democratizing large language model-based graph data augmentation via latent knowledge graphs","volume":"191","author":"Feng","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109162_bib0014","series-title":"Gpt4graph: Can large language models understand graph structured data? An empirical evaluation and benchmarking","author":"Guo","year":"2023"},{"key":"10.1016\/j.neunet.2026.109162_bib0015","article-title":"Inductive representation learning on large graphs","volume":"30","author":"Hamilton","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109162_bib0016","series-title":"Explanations as features: Llm-based features for text-attributed graphs","first-page":"1","volume":"2","author":"He","year":"2023"},{"key":"10.1016\/j.neunet.2026.109162_bib0017","series-title":"Harnessing explanations: Llm-to-lm interpreter for enhanced text-attributed graph representation learning","author":"He","year":"2023"},{"key":"10.1016\/j.neunet.2026.109162_bib0018","series-title":"Unigraph: Learning a unified cross-domain foundation model for text-attributed graphs","author":"He","year":"2024"},{"key":"10.1016\/j.neunet.2026.109162_bib0019","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2025.108089","article-title":"A vision-language model for multitask classification of memes","volume":"194","author":"Hossain","year":"2026","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109162_bib0020","series-title":"Proceedings of the ACM web conference 2023","first-page":"737","article-title":"Graphmae2: A decoding-enhanced masked self-supervised graph learner","author":"Hou","year":"2023"},{"key":"10.1016\/j.neunet.2026.109162_bib0021","first-page":"22118","article-title":"Open graph benchmark: Datasets for machine learning on graphs","volume":"33","author":"Hu","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109162_bib0022","series-title":"Proceedings of the ACM on web conference 2024","first-page":"893","article-title":"Can GNN be good adapter for LLMs?","author":"Huang","year":"2024"},{"key":"10.1016\/j.neunet.2026.109162_bib0023","series-title":"Self-supervised learning on graphs: Deep insights and new direction","author":"Jin","year":"2020"},{"key":"10.1016\/j.neunet.2026.109162_bib0024","first-page":"21798","article-title":"Hard negative mixing for contrastive learning","volume":"33","author":"Kalantidis","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109162_bib0025","series-title":"Proceedings of the web conference 2020","first-page":"2878","article-title":"Multimodal post attentive profiling for influencer marketing","author":"Kim","year":"2020"},{"key":"10.1016\/j.neunet.2026.109162_bib0026","series-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"issue":"13","key":"10.1016\/j.neunet.2026.109162_bib0027","doi-asserted-by":"crossref","first-page":"3521","DOI":"10.1073\/pnas.1611835114","article-title":"Overcoming catastrophic forgetting in neural networks","volume":"114","author":"Kirkpatrick","year":"2017","journal-title":"Proceedings of the National Academy of Sciences"},{"key":"10.1016\/j.neunet.2026.109162_bib0028","series-title":"Gofa: A generative one-for-all model for joint graph language modeling","author":"Kong","year":"2024"},{"key":"10.1016\/j.neunet.2026.109162_bib0029","series-title":"The power of scale for parameter-efficient prompt tuning","author":"Lester","year":"2021"},{"key":"10.1016\/j.neunet.2026.109162_bib0030","series-title":"Prefix-tuning: Optimizing continuous prompts for generation","author":"Li","year":"2021"},{"key":"10.1016\/j.neunet.2026.109162_bib0031","series-title":"Proceedings of the 30th ACM SIGKDD conference on knowledge discovery and data mining","first-page":"1725","article-title":"Zerog: Investigating cross-dataset zero-shot transferability in graphs","author":"Li","year":"2024"},{"key":"10.1016\/j.neunet.2026.109162_bib0032","series-title":"Evaluating large language models on graphs: Performance insights and comparative analysis","author":"Liu","year":"2023"},{"key":"10.1016\/j.neunet.2026.109162_bib0033","series-title":"One for all: Towards training one graph model for all classification tasks","author":"Liu","year":"2023"},{"key":"10.1016\/j.neunet.2026.109162_bib0034","series-title":"Towards graph foundation models: A survey and beyond","author":"Liu","year":"2023"},{"key":"10.1016\/j.neunet.2026.109162_bib0035","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1016\/j.aiopen.2023.08.012","article-title":"Gpt understands, too","volume":"5","author":"Liu","year":"2023","journal-title":"AI Open"},{"key":"10.1016\/j.neunet.2026.109162_bib0036","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"8868","article-title":"Spectral-based graph neural networks for complementary item recommendation","volume":"vol. 38","author":"Luo","year":"2024"},{"issue":"2","key":"10.1016\/j.neunet.2026.109162_bib0037","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3605943","article-title":"Recent advances in natural language processing via large pre-trained language models: A survey","volume":"56","author":"Min","year":"2023","journal-title":"ACM Computing Surveys"},{"key":"10.1016\/j.neunet.2026.109162_bib0038","series-title":"Discovering language model behaviors with model-written evaluations","author":"Perez","year":"2022"},{"issue":"140","key":"10.1016\/j.neunet.2026.109162_bib0039","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"issue":"8","key":"10.1016\/j.neunet.2026.109162_bib0040","doi-asserted-by":"crossref","first-page":"8846","DOI":"10.1109\/TITS.2023.3257759","article-title":"Graph neural networks for intelligent transportation systems: A survey","volume":"24","author":"Rahmani","year":"2023","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"key":"10.1016\/j.neunet.2026.109162_bib0041","series-title":"Sentence-bert: Sentence embeddings using siamese bert-networks","author":"Reimers","year":"2019"},{"key":"10.1016\/j.neunet.2026.109162_bib0042","series-title":"Contrastive learning with hard negative samples","author":"Robinson","year":"2020"},{"issue":"5","key":"10.1016\/j.neunet.2026.109162_bib0043","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3722561","article-title":"Ma-gcl4sr: Improving graph contrastive learning-based sequential recommendation with model augmentation","volume":"19","author":"Sang","year":"2025","journal-title":"ACM Transactions on Knowledge Discovery from Data"},{"key":"10.1016\/j.neunet.2026.109162_bib0044","series-title":"Masked label prediction: Unified message passing model for semi-supervised classification","author":"Shi","year":"2020"},{"key":"10.1016\/j.neunet.2026.109162_bib0045","article-title":"Graph-oriented instruction tuning of large language models for generic graph mining","author":"Tan","year":"2025","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.1016\/j.neunet.2026.109162_bib0046","series-title":"International conference on machine learning","first-page":"21076","article-title":"Rethinking graph neural networks for anomaly detection","volume":"162","author":"Tang","year":"2022"},{"key":"10.1016\/j.neunet.2026.109162_bib0047","series-title":"Proceedings of the 47th international ACM SIGIR conference on research and development in information retrieval","first-page":"491","article-title":"Graphgpt: Graph instruction tuning for large language models","author":"Tang","year":"2024"},{"key":"10.1016\/j.neunet.2026.109162_bib0048","series-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"10.1016\/j.neunet.2026.109162_bib0049","series-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017"},{"key":"10.1016\/j.neunet.2026.109162_bib0050","first-page":"30840","article-title":"Can language models solve graph problems in natural language?","volume":"36","author":"Wang","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"3","key":"10.1016\/j.neunet.2026.109162_bib0051","doi-asserted-by":"crossref","first-page":"279","DOI":"10.1038\/s42256-022-00447-x","article-title":"Molecular contrastive learning of representations via graph neural networks","volume":"4","author":"Wang","year":"2022","journal-title":"Nature Machine Intelligence"},{"issue":"9","key":"10.1016\/j.neunet.2026.109162_bib0052","first-page":"1","article-title":"A survey on knowledge graph related research in smart city domain","volume":"18","author":"Wang","year":"2024","journal-title":"ACM Transactions on Knowledge Discovery from Data"},{"key":"10.1016\/j.neunet.2026.109162_bib0053","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.ddtec.2020.11.009","article-title":"A compact review of molecular property prediction with graph neural networks","volume":"37","author":"Wieder","year":"2020","journal-title":"Drug Discovery Today: Technologies"},{"key":"10.1016\/j.neunet.2026.109162_bib0054","series-title":"International conference on machine learning","first-page":"6861","article-title":"Simplifying graph convolutional networks","author":"Wu","year":"2019"},{"key":"10.1016\/j.neunet.2026.109162_bib0055","series-title":"2023 IEEE international conference on big data (bigdata)","first-page":"2247","article-title":"Multimodal large language models: A survey","author":"Wu","year":"2023"},{"key":"10.1016\/j.neunet.2026.109162_bib0056","first-page":"27387","article-title":"Nodeformer: A scalable graph structure learning transformer for node classification","volume":"35","author":"Wu","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109162_bib0057","series-title":"Proceedings of the ACM web conference 2022","first-page":"1070","article-title":"Simgrace: A simple framework for graph contrastive learning without data augmentation","author":"Xia","year":"2022"},{"key":"10.1016\/j.neunet.2026.109162_bib0058","series-title":"Proceedings of the ACM web conference 2023","first-page":"992","article-title":"Automated self-supervised learning for recommendation","author":"Xia","year":"2023"},{"key":"10.1016\/j.neunet.2026.109162_bib0059","series-title":"Proceedings of the AAAI conference on artificial intelligence","first-page":"12881","article-title":"Improving complex reasoning over knowledge graph with logic-aware curriculum tuning","volume":"vol. 39","author":"Xia","year":"2025"},{"issue":"5","key":"10.1016\/j.neunet.2026.109162_bib0060","first-page":"1","article-title":"Tapping the potential of large language models as recommender systems: A comprehensive framework and empirical analysis","volume":"19","author":"Xu","year":"2025","journal-title":"ACM Transactions on Knowledge Discovery from Data"},{"key":"10.1016\/j.neunet.2026.109162_bib0061","series-title":"Proceedings of the ACM web conference 2022","first-page":"2501","article-title":"Evidence-aware fake news detection with graph neural networks","author":"Xu","year":"2022"},{"key":"10.1016\/j.neunet.2026.109162_bib0062","series-title":"Qwen3 technical report","author":"Yang","year":"2025"},{"key":"10.1016\/j.neunet.2026.109162_bib0063","series-title":"Proceedings of the 44th international ACM SIGIR conference on research and development in information retrieval","first-page":"2141","article-title":"Consisrec: Enhancing gnn for social recommendation via consistent neighbor aggregation","author":"Yang","year":"2021"},{"key":"10.1016\/j.neunet.2026.109162_bib0064","series-title":"International conference on machine learning","first-page":"40","article-title":"Revisiting semi-supervised learning with graph embeddings","author":"Yang","year":"2016"},{"key":"10.1016\/j.neunet.2026.109162_bib0065","series-title":"Natural language is all a graph needs","author":"Ye","year":"2023"},{"key":"10.1016\/j.neunet.2026.109162_bib0066","series-title":"A survey on multimodal large language models","author":"Yin","year":"2023"},{"key":"10.1016\/j.neunet.2026.109162_bib0067","first-page":"5812","article-title":"Graph contrastive learning with augmentations","volume":"33","author":"You","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"10.1016\/j.neunet.2026.109162_bib0068","series-title":"Instruction tuning for large language models: A survey","author":"Zhang","year":"2023"},{"key":"10.1016\/j.neunet.2026.109162_bib0069","series-title":"Graphtext: Graph reasoning in text space","author":"Zhao","year":"2023"},{"key":"10.1016\/j.neunet.2026.109162_bib0070","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1016\/j.neunet.2021.04.002","article-title":"End-to-end keyword search system based on attention mechanism and energy scorer for low resource languages","volume":"139","author":"Zhao","year":"2021","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109162_bib0071","doi-asserted-by":"crossref","DOI":"10.1016\/j.neunet.2024.107078","article-title":"Diccr: Double-gated intervention and confounder causal reasoning for vision-language navigation","volume":"184","author":"Zhou","year":"2025","journal-title":"Neural Networks"},{"key":"10.1016\/j.neunet.2026.109162_bib0072","series-title":"Proceedings of the web conference 2021","first-page":"2069","article-title":"Graph contrastive learning with adaptive augmentation","author":"Zhu","year":"2021"}],"container-title":["Neural Networks"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026006234?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0893608026006234?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T11:57:30Z","timestamp":1780401450000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0893608026006234"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":72,"alternative-id":["S0893608026006234"],"URL":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109162","relation":{},"ISSN":["0893-6080"],"issn-type":[{"value":"0893-6080","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Enhance graph alignment for large language models","name":"articletitle","label":"Article Title"},{"value":"Neural Networks","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neunet.2026.109162","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Ltd.","name":"copyright","label":"Copyright"}],"article-number":"109162"}}