基于大语言模型的图学习综述:方法、基准与进展

doi:10.11896/jsjkx.260400039

摘要/Abstract

摘要： 大语言模型凭借强大的语义理解与知识推理能力,为突破传统图学习在零样本推理与跨领域迁移上的泛化瓶颈提供了重要路径,但现有研究缺乏对大语言模型赋能图学习的方法体系与评测基准的系统性分析。对此,梳理该领域三阶段发展脉络,并基于协同层级与图结构类型构建二维分类框架:前者涵盖仅依赖大语言模型的图建模、大语言模型与图神经网络分层协同及深度协同3类模式,深入剖析各类方法的核心机制与适用边界;后者聚焦大语言模型在文本属性图、多模态图、异构图与动态图等复杂结构下的适配机制。在此基础上,概括推荐系统、异常检测等典型应用中大语言模型赋能图学习的进展,从交互方式与任务类型等方面归纳现有基准并分析各类方法的能力边界。结果表明,协同方法通常更稳健,现有评测体系在动态基准构建与结构感知衰减量化等方面仍有不足。最后,总结当前研究在大规模时空图、跨场景泛化、效能优化与可信安全方面的挑战,并展望未来研究方向。

关键词: 图学习, 大语言模型, 图神经网络, 跨模态对齐

Abstract: Large language models(LLMs),with their strong semantic understanding and knowledge reasoning capabilities,offer a promising pathway for overcoming the generalization bottlenecks of traditional graph learning in zero-shot reasoning and cross-domain transfer.However,existing studies lack a systematic analysis of the methodological framework and evaluation benchmarks for LLM-empowered graph learning.This paper reviews the three-stage development trajectory of this field and constructs a two-dimensional taxonomy based on collaboration level and graph structure type.The collaboration dimension covers three paradigms:LLM-only graph modeling,layered LLM-GNN collaboration,and deep integration paradigms,with a detailed analysis of the core mechanisms,applicability,and limitations of each.The graph structure dimension focuses on the adaptation mechanisms of LLMs for complex topologies,including text-attributed graphs,multimodal graphs,heterogeneous graphs,and dynamic graphs.Building upon this foundation,progress in typical applications such as recommender systems and anomaly detection is summarized.Furthermore,it systematically reviews existing benchmarks from the perspectives of LLM interaction modes and task types,highlighting the capability boundaries of different methods.Results indicate that collaborative schemes are generally more robust,while current evaluation systems remain insufficient in areas such as dynamic benchmark construction and quantitative assessment of structural perception decay.Finally,the paper summarizes current challenges regarding large-scale spatiotemporal graphs,cross-scenario generalization,efficiency optimization,and trustworthiness and security,and outlines future research directions.

Key words: Graph learning, Large language models, Graph neural networks, Cross-modal alignment

中图分类号:

TP391

贺娇君, 李欣. 基于大语言模型的图学习综述:方法、基准与进展[J]. 计算机科学, 2026, 53(9): 1-15. https://doi.org/10.11896/jsjkx.260400039

HE Jiaojun, LI Xin. Review of Graph Learning Based on Large Language Models:Methods,Benchmarks and Advances[J]. Computer Science, 2026, 53(9): 1-15. https://doi.org/10.11896/jsjkx.260400039

参考文献

[1] REN X,WEI W,XIA L,et al.A comprehensive survey on self-supervised learning for recommendation[J].ACM Computing Surveys,2026,58(1):1-38.
[2] WANG Z,YU D,SHEN S,et al.Select your own counterparts:Self-supervised graph contrastive learning with positive sampling[J].IEEE Transactions on Neural Networks and Learning Systems,2025,36(4):6858-6872.
[3] HUANG Z,ZHOU W,JIANG Y,et al.An efficient community-aware pre-training method for graph neural networks[J].Pattern Recognition,2026,172:112340.
[4] KIPF T N,WELLING M.Semi-supervised classification withgraph convolutional networks[J].arXiv:1609.02907,2017.
[5] SHANG W,HUANG X.A survey of large language models on generative graph analytics:Query,learning,and applications[J].IEEE Transactions on Knowledge and Data Engineering,2025,37(12):6799-6819.
[6] PEROZZI B,AL-RFOU R,SKIENA S.DeepWalk:Online learning of social representations[C] //Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.ACM,2014:701-710.
[7] GROVER A,LESKOVEC J.node2vec:Scalable feature learning for networks[C] //Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.San Francisco:ACM,2016:855-864.
[8] LI F,ZHANG L,ZUO Y,et al.Beyond one-size-fits-all:adaptive subgraph denoising for zero-shot graph learning with large language models[J].arXiv:2603.02938,2026.
[9] SHEHZAD A,XIA F,ABID S,et al.Graph transformers:Asurvey[J].arXiv:2407.09777,2026.
[10] OPENAI,ACHIAM J,ADLER S,et al.GPT-4 technical report[J].arXiv:2303.08774,2024.
[11] GRATTAFIORI A,DUBEY A,JAUHRI A,et al.The llama 3 herd of models[J].arXiv:2407.21783,2024.
[12] DEEPSEEK-AI,LIU A,FENG B,et al.DeepSeek-V3 technical report[J].arXiv:2412.19437,2025.
[13] CHIEN E,CHANG W C,HSIEH C J,et al.Node feature extraction by self-supervised multi-scale neighborhood prediction[C] //ICLR.2022.
[14] LIU H,FENG J,KONG L,et al.One for all:towards training one graph model for all classification tasks[C] //ICLR.2024.
[15] HE X,BRESSON X,LAURENT T,et al.Harnessing explanations:LLM-to-LM interpreter for enhanced text-attributed graph representation learning[C] //ICLR.2024.
[16] GUO J,DU L,LIU H,et al.GPT4Graph:can large languagemodels understand graph structured data？An empirical evaluation and benchmarking[J].arXiv:2305.15066,2023.
[17] SUN Y,MA Z,FANG Y,et al.GraphICL:unlocking graph learning potential in LLMs through structured prompt design[C] //NAACL 2025.2025:2440-2459.
[18] TANG J,YANG Y,WEI W,et al.GraphGPT:Graph instruction tuning for large language models[C] //Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval.Washington DC USA:ACM,2024:491-500.
[19] ZHANG M,SUN M,WANG P,et al.GraphTranslator:aligning graph model to large language model for open-ended tasks[C] //Proceedings of the ACM Web Conference 2024.2024:1003-1014.
[20] MA S,XU C,JIANG X,et al.Think-on-graph 2.0:deep andfaithful large language model reasoning with knowledge-guided retrieval augmented generation[C] //ICLR 2025.2025.
[21] FINKELSHTEIN B,CUCERZAN S,JAUHAR S K,et al.Actions speak louder than prompts:a large-scale study of LLMs for graph inference[C] //ICLR 2026.2026.
[22] WANG Y,FAN W,WANG S,et al.Towards graph foundation models:a transferability perspective[J].arXiv:2503.09363,2025.
[23] WANG Z,LIU Z,MA T,et al.Graph foundation models:a comprehensive survey[J].arXiv:2505.25116,2025.
[24] LIU J,YANG C,LU Z,et al.Graph foundation models:Con-cepts,opportunities and challenges[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2025,47(6):5023-5044.
[25] KONG L,FENG J,LIU H,et al.Gofa:A generative one-for-all model for joint graph language modeling[J].arXiv:2407.09709,2025.
[26] WANG Z,ZHANG Z,MA T,et al.Towards graph foundation models:learning generalities across graphs via task-trees[J].arXiv:2407.09709,2025.
[27] HE Y,SUI Y,HE X,et al.UniGrapH2:Learning a unified embedding space to bind multimodal graphs[C] //Proceedings of the ACM on Web Conference 2025.ACM,2025:1759-1770.
[28] ZHA X,DONG Y,JIANG H,et al.LLM-AGR:Large language model augmented graph representation learning for recommendation[J].Knowledge-Based Systems,2025,331:114791.
[29] LI Y,HU J,HOOI B,et al.DGP:a dual-granularity prompting framework for fraud detection with graph-enhanced LLMs[J].arXiv:2507.21653,2025.
[30] XIE L,JIN Y,XU L,et al.Fusing domain knowledge with afine-tuned large language model for enhanced molecular property prediction[J].Journal of Chemical Theory and Computation,2025,21(14):6743-6758.
[31] FANG Y,FAN D,ZHA D,et al.GAugLLM:improving graph contrastive learning for text-attributed graphs with large language models[J].arXiv:2406.11945,2024.
[32] REN X,TANG J,YIN D,et al.A survey of large language models for graphs[C] //Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.2024:6616-6626.
[33] LI Y,LI Z,WANG P,et al.A survey of graph meets large language model:progress and future directions[C] //IJCAI.2024.
[34] JIN B,LIU G,HAN C,et al.Large language models on graphs:A comprehensive survey[J].IEEE Transactions on Knowledge and Data Engineering,2024,36(12):8622-8642.
[35] ZHU X,YANG C,WANG Q,et al.Graph4LLM:a systematic survey of graph-enhanced large language models[J/OL].(2026-02-13)[2026-05-06].http://www.shichuan.org/doc/215.pdf.
[36] FATEMI B,HALCROW J,PEROZZI B.Talk like a graph:Encoding graphs for large language models[C] //ICLR 2024.2024.
[37] ZHAO J,ZHUO L,SHEN Y,et al.GraphText:Graph reasoning in text space[C] //NeurIPS 2024.2024.
[38] WANG H,FENG S,HE T,et al.Can language models solvegraph problems in natural language?[C] //Proceedings of the 37th International Conference on Neural Information Processing System.2023:30840-30861.
[39] HERBST D,KARBEVSKA L,KUMAR D,et al.Lost in serialization:Invariance and generalization of LLM graph reasoners[J].arXiv:2511.10234,2025.
[40] YE R,ZHANG C,WANG R,et al.Language is all a graphneeds[C] //EACL 2024.2024:1955-1973.
[41] LEE H,YI C,ISLAM M,et al.Scalability matters:overcoming challenges in InstructGLM with similarity-degree-based sampling[C] //2025 International Joint Conference on Neural Networks.IEEE,2025.
[42] TAN Y,LV H,ZHAN P,et al.Graph-oriented instruction tuning of large language models for generic graph mining[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,2026,48(1):155-169.
[43] WANG J,WU J,HOU Y,et al.InstructGraph:boosting largelanguage models via graph-centric instruction tuning and preference alignment[J].arXiv:2402.08785,2024.
[44] CHEN N,LI Y,TANG J,et al.GraphWiz:An instruction-following language model for graph computational problems[C] //Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.Barcelona Spain:ACM,2024:353-364.
[45] JI Y,LIU C,CHEN X,et al.From anchors to answers:A novel node tokenizer for integrating graph structure into large language models[C] //Proceedings of the 34th ACM International Conference on Information and Knowledge Management.Seoul Republic of Korea:ACM,2025:1124-1134.
[46] WU Y,LU G,ZUO Y,et al.Graph-R1:incentivizing the zero-shot graph learning capability in LLMs via explicit reasoning[C] //Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing.2025:23909-23927.
[47] LIU J,YI B,ZHANG H,et al.Modeling semantic representa-tion with LLM-enhanced for knowledge-aware recommendation[J].Information Processing & Management,2026,63(2):104387.
[48] KE L.TKG-LLM:Temporal Knowledge Graph as EnhancedPrompt Learning with LLM for Time Series Forecasting[J].Information Fusion,2026,125:103520.
[49] YANG C,LIU H,WANG D,et al.FLAG:Fraud detection with LLM-enhanced graph neural network[C] //Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2.Toronto ON Canada:ACM,2025:5150-5160.
[50] JAISWAL A,CHOUDHARY N,ADKATHIMAR R,et al.All against some:efficient integration of large language models for message passing in graph neural networks[J].arXiv:2407.14996,2024.
[51] ZHANG Z,LI X,LI R H,et al.Toward general and robust LLM-enhanced text-attributed graph learning[J].arXiv:2504.02343,2025.
[52] GUO Z,XIA L,YU Y,et al.GraphEdit:large language models for graph structure learning[J].arXiv:2402.25283,2025.
[53] CHEN R,ZHAO T,JAISWAL A,et al.LLaGA:large language and graph assistant[J].arXiv:2402.08270,2024.
[54] MAVROMATIS C,KARYPIS G.GNN-RAG:Graph neural retrieval for efficient large language model reasoning on knowledge graphs[C] //ACL 2025.2025:16682-16699.
[55] WU L,QIU Z,ZHENG Z,et al.Exploring large language model for graph data understanding in online job recommendations[J].Proceedings of the AAAI Conference on Artificial Intelligence,2024,38(8):9178-9186.
[56] LUO L,LI Y F,HAFFARI G,et al.Reasoning on graphs:Faithful and inter- pretable large language model reasoning[J].arXiv:2310.01016,2024.
[57] HE X,TIAN Y,SUN Y,et al.G-retriever:Retrieval-augmented generation for textual graph understanding and question answering[C] //NeurIPS 2024.2024.
[58] LEE C,KO H,SONG Y,et al.Mol-LLM:multimodal generalist molecular LLM with improved graph utilization[J].arXiv:2502.02810,2025.
[59] LI Y,LIU C,GAO X,et al.MolPrompt:Improving multi-modal molecular pre-training with knowledge prompts[J].Bioinformatics,2025,41(9):btaf466.
[60] BRANNON W,KANG W,FULAY S,et al.ConGraT:Self-supervised contrastive pretraining for joint graph and text embeddings[C] //Proceedings of TextGraphs-17:Graph-based Methods for Natural Language Processing.Bangkok,Thailand:Association for Computational Linguistics,2024:19-39.
[61] RADFORD A,KIM J W,HALLACY C,et al.Learning transferable visual models from natural language supervision[C] //International Conference on Machine Learning.2021:8748-8763.
[62] ZHAO J,QU M,LI C,et al.Learning on large-scale text-attributed graphs via variational inference[J].arXiv:2210.14709,2023.
[63] GUAN Z,ZHAO H,WU L,et al.LangTopo:aligning language descriptions of graphs with tokenized topological modeling[J].arXiv:2406.13250,2024.
[64] LV R,ZHANG Z,ZHANG K,et al.GraphPrompter:multi-stage adaptive prompt optimization for graph in-context learning[J].arXiv:2505.02027,2025.
[65] LI J,SUN X,LI Y,et al.Graph intelligence with large language models and prompt learning[C] //Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.Barcelona Spain:ACM,2024:6545-6554.
[66] HU S,ZOU G,YANG S,et al.Large language model meetsgraph neural network in knowledge distillation[C] //Proceedings of the AAAI Conference on Artificial Intelligence.2025:17295-17304.
[67] XU J,WU Z,LIN M,et al.LLM and GNN are complementary:distilling LLM for multimodal graph learning[C] //2025 IEEE International Conference on Big Data(BigData).IEEE,2024.
[68] YANG H,WANG X,TAO Q,et al.GL-fusion:rethinking the combination of graph neural network and large language model[J].arXiv:2412.06849,2024.
[69] ZHU Y,WANG Y,SHI H,et al.Efficient tuning and inference for large language models on textual graphs[C] //IJCAI 2024.2024:5734-5742.
[70] HUANG X,HAN K,YANG Y,et al.Can GNN be good adapterfor LLMs?[C] //Proceedings of the ACM Web Conference 2024.Singapore Singapore:ACM,2024:893-904.
[71] BEIRANVAND A,VAHIDIPOUR S M.Integrating structural and semantic signals in text-attributed graphs with BiGTex[J].Machine Learning with Applications,2026,24:100921.
[72] SU G,WANG H,WANG J,et al.Large language models meettext-attributed graphs:a survey of integration frameworks and applications[J].arXiv:2510.21131,2025.
[73] WANG Z,LIU S,ZHANG Z,et al.Can LLMs convert graphs to text-attributed graphs?[C] //Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics:Human Language Technologies(Volume 1:Long Papers).2025:1412-1432.
[74] HU Z,LI Y,CHEN Z,et al.Let’s ask GNN:Empowering large language model for graph in-context learning[C] //Findings of the Association for Computational Linguistics:EMNLP 2024.Miami,Florida,USA:Association for Computational Linguistics,2024:1396-1409.
[75] WANG D,ZUO Y,LI F,et al.LLMs as zero-shot graph learners:Alignment of GNN representations with LLM token embeddings[C] //NeurIPS 2024.2024.
[76] PAN B,ZHANG Z,ZHANG Y,et al.Distilling large language models for text-attributed graph learning[C] //Proceedings of the 33rd ACM International Conference on Information and Knowledge Management.Boise ID USA:ACM,2024:1836-1845.
[77] LI X,LIAN D,LU Z,et al.GraphAdapter:Tuning vision-lan-guage models with dual knowledge graph[C] //NeurIPS 2023.2023.
[78] FANG Y,JIN B,SHEN J,et al.GraphGPT-o:Synergistic multimodal comprehension and generation on graphs[C] //2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition(CVPR).Nashville,TN,USA:IEEE,2025:19467-19476.
[79] WANG X,ZHANG Z,XIAO L,et al.Towards multimodalgraph large language model[J].Science China Information Sciences,2025,68(11):213101.
[80] WANG S,HUANG J,CHEN Z,et al.Graph machine learning in the era of large language models(LLMs)[J].ACM Transactions on Intelligent Systems and Technology,2025,16(5):1-40.
[81] FANG R,SUN Y,YUAN J,et al. A language-assisted semantic-aware disentangled method for link prediction on heterogeneous graphs[C] //Proceedings of the 33rd ACM International Conference on Multimedia.Dublin,Ireland:ACM,2025:2352-2361.
[82] GAO H,ZHANG C,WU F,et al.Bootstrapping heterogeneous graph representation learning via large language models:a generalized approach[C] //Proceedings of the AAAI Conference on Artificial Intelligence.2025:16717-16726..
[83] TANG J,YANG Y,WEI W,et al.HiGPT:Heterogeneousgraph language model[C] //Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.Barcelona Spain:ACM,2024:2842-2853.
[84] LI W,ZHENG T,LIU S,et al.Towards efficient LLM-aware heterogeneous graph learning[J].arXiv:2511.17923,2025.
[85] SINHA A.GMLM:bridging graph neural networks and lan-guage models for heterophilic node classification[J].arXiv:2503.05763,2025.
[86] ZHANG Z,WANG X,ZHANG Z,et al.LLM4DyG:Can large language models solve spatial-temporal problems on dynamic graphs?[C] //Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining.Barcelona Spain:ACM,2024:4350-4361.
[87] ZHAO Z,LIN F,ZHU X,et al.DynLLM:when large language models meet dynamic graph recommendation[J].arXiv:2405.07580,2024.
[88] WANG Q,GAO Z,XU R.Graph agent:explicit reasoning agent for graphs[J].arXiv:2310.16421,2023.
[89] YANG Y,TANG J,XIA L,et al.GraphAgent:Agentic graphlanguage assistant[C] //Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing.2025:26349-26368.
[90] LIU Y,ZHANG G,WANG K,et al.Graph-augmented largelanguage model agents:current progress and future prospects[J].IEEE Intelligent Systems,2026,41(2):45-55.
[91] LEI R,JI J,DING H,et al.Exploring the potential of large language models as predictors in dynamic text-attributed graphs[J].arXiv:2503.03258,2025.
[92] WU J,ZHAO Q,CHEN Z,et al.GAP:graph-based agent planning with parallel tool use and reinforcement learning[J].arXiv:2510.25320,2025.
[93] WEI W,REN X,TANG J,et al.LLMRec:large language mo-dels with graph augmentation for recommendation[C] //Proceedings of the 17th ACM International Conference on Web Search and Data Mining.2024:806-815.
[94] PENG Q,CAO B,XIE X,et al.LLMSRec:Large language model with service network augmentation for web service recommendation[J].Knowledge-Based Systems,2025,323:113710.
[95] QIU Z,LUO L,ZHAO Z,et al.Graph retrieval-augmented LLM for conversational recommendation systems[C] //Advances in Knowledge Discovery and Data Mining.Singapore:Springer Nature Singapore,2025:344-355.
[96] LI Y,ZHANG X,LUO L,et al.G-refer:graph retrieval-augmented large language model for explainable recommendation[C] //Proceedings of the ACM on Web Conference 2025.2025:240-251.
[97] YUAN Y,CHEN M,WU A B,et al.Graph anomaly detection model based on personalized PageRank and contrastive learning[J].Computer Science,2025,52(2):80-90.
[98] CHOI R Y,SONG Y,JANG M,et al.Smart contract vulnerability detection using large language models and graph structural analysis[J].Computers,Materials & Continua,2025,83(1):785-801.
[99] XU Y,CHEN J,PENG Z,et al.Court of LLMs:evidence-augmented generation via multi-LLM collaboration for text-attributed graph anomaly detection[J].arXiv:2508.00507,2025.
[100] BELCASTRO L,CARLUCCI C,COSENTINO C,et al.Enhancing network security using knowledge graphs and large language models for explainable threat detection[J].Future Gene-ration Computer Systems,2026,176:108160.
[101] FU F,LI Q Q,WANG F,et al.Synergizing a knowledge graph and large language model for relay catalysis pathway recommendation[J].National Science Review,2025,12(8):nwaf271.
[102] LI Y,GUPTA V,KILIC M N T,et al.Hybrid-LLM-GNN:Integrating large language models and graph neural networks for enhanced materials property prediction[J].Digital Discovery,2025,4(2):376-383.
[103] HUANG J,ZHANG X,MEI Q,et al.Can LLMs effectively leverage graph structural information through prompts,and why?[J].arXiv:2309.16595,2024.
[104] LIU C,WU B.Evaluating large language models on graphs:performance insights and comparative analysis[J].arXiv:2308.11224,2023.
[105] DAI X,QU H,SHEN Y,et al.How do large language models understand graph patterns? A benchmark for graph pattern comprehension[J].arXiv:2410.05298,2025.
[106] ZHANG Y,WANG H,FENG S,et al.Can LLM graph reasoning generalize beyond pattern memorization?[C] //Findings of the Association for Computational Linguistics:EMNLP 2024.Miami,Florida,USA:Association for Computational Linguistics,2024:2289-2305.
[107] CAO Y,HAN S,GAO Z,et al.GraphInsight:Unlocking insights in large language models for graph structure understanding[C] //Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics(Volume 1:Long Papers).2025:12096-12134.
[108] CHAI Z,ZHANG T,WU L,et al.GraphLLM:Boosting graph reasoning ability of large language model[J].IEEE Transactions on Big Data,2026,12(2):475-483.
[109] LUO Z,SONG X,HUANG H,et al.GraphInstruct:empowering large language models with graph understanding and reasoning capability[J].arXiv:2403.04483,2025.
[110] LI Y,WANG P,ZHU X,et al.GLBench:a comprehensivebenchmark for graph with large language models[C] //NeurIPS 2024.2024.
[111] FENG T,SUN Y,YOU J.GraphEval:a lightweight graph-based LLM framework for idea evaluation[C] //ICLR.2025.
[112] LI X,CHEN W,CHU Q,et al.Can large language models analyze graphs like professionals? A benchmark,datasets and models[C] //NeurIPS 2025.2025.
[113] HU Y,HUANG X,WEI Z,et al.Rethinking and benchmarking large language models for graph reasoning[J].arXiv:2509.24260,2025.
[114] WU Q,CHEN Z,CORCORAN W,et al.GraphEval2000:Benchmarking and Improving Large Language Models on Graph Datasets[J].arXiv:2406.16176,2025.
[115] WU Q,CHEN Z,CORCORAN W,et al.GraphEval36K:Benchmarking coding and reasoning capabilities of large language models on graph datasets[C] //NAACL 2025.2025:8110-8132.
[116] DUAN H,CHENG Y,YU J,et al.Can large language models act as ensembler for multi-GNNs?[C] //Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing.2025:28875-28894.
[117] CHU X,XUE H,TAN Z,et al.GraphSOS:graph sampling and order selection to help LLMs understand graphs better[J].arXiv:2501.14427,2025.
[118] CAI Q,WANG Z,DIAO S,et al.CodeGraph:enhancing graph reasoning of LLMs with code[J].arXiv:2408.13863,2024.
[119] YUAN Z,LIU M,WANG H,et al.GraCoRe:benchmarkinggraph comprehension and complex reasoning in large language models[C] //Proceedings of the 31st International Conference on Computational Linguistics.2025:7925-7948.
[120] LI H,JYOTHI K S,LIANG H,et al.Zero-shot graph reasoning via retrieval augmented framework with LLMs[J].arXiv:2509.12743.2025.
[121] GUAN Z,WU L,ZHAO H,et al.Attention mechanisms per-spective:exploring LLM processing of graph-structured data[J].arXiv:2505.02130,2025.
[122] XU H,YOU Y,MA T.When structure doesn’t help:LLMs do not read text-attributed graphs as effectively as we expected[J].arXiv:2511.16767,2025.
[123] ZHANG T,YANG R,LAI Y,et al.Leveraging large language models for effective label-free node classification in text-attributed graphs[C] //Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval.2025:698-708.
[124] XUE R,DENG H,HE F,et al.Trustworthy GNNs with LLMs:a systematic review and taxonomy[J].arXiv:2502.08353,2025.
[125] DONG Y,WANG S,LEI Z,et al.A benchmark for fairness- aware graph learning[J].arXiv:2407.12112,2024.
[126] YU S,WANG Y,LI R,et al.GrapH2text or Graph2token:A perspective of large language models for graph learning[J].ACM Transactions on Information Systems,2025,44(3):1-49.
[127] JAVED R,KAY J,YANNI D,et al.Do LLMs exhibit demographic parity in responses to queries about human rights?[J].arXiv:2502.19463,2025.
[128] XU X,HE X,ZHI C,et al.BiasFreeBench:a benchmark for mitigating bias in large language model responses[J].arXiv:2510.00232,2025.
[129] DWIVEDI V P,JALADI S,SHEN Y,et al.Relational graphtransformer[J].arXiv:2505.10960,2026.
[130] ZHU Q,ZHENG D,SONG X.Parameter-efficient tuning large language models for graph representation learning[J].arXiv:2404.18271,2024.
[131] WANG Z,ZHANG C,LI J,et al.Graph foundation models:Challenges,methods,and open questions[C] //Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2.Toronto ON Canada:ACM,2025:6184-6194.
[132] BO J,WU H,FANG Y.Quantizing text-attributed graphs forsemantic-structural integration[C] //Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2.Toronto ON Canada:ACM,2025:107-118.
[133] ZHANG Q,SHENG X,SUN Y,et al.TrustGLM:Evaluating the robustness of GraphLLMs against prompt,text,and structure attacks[C] //Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining.ACM,2025:5912-5923.
[134] YAN B,ZHANG Z,SUN H,et al.Data-centric federated graph learning with large language models[J].arXiv:2503.19455,2025.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed