Elamur Research⌕
☰
home / papers / 2026 / 大模型驱动的文本属性图学习研究进展

大模型驱动的文本属性图学习研究进展

Summary

Text-attributed graphs (TAGs) attach natural-language content to nodes and edges. Examples include paper abstracts in citation networks, user profiles in social networks and product descriptions in e-commerce knowledge graphs. Conventional GNN pipelines usually compress this text into shallow, context-free vectors such as Bag-of-Words or Word2Vec. These vectors miss polysemy and context, and they make it hard to combine structural and semantic signals.

This survey from Renmin University maps the growing body of work that uses large models to address these limits. Earlier reviews mostly covered prediction tasks within a GNN-centric framing. This one spans three task families: graph generation, graph prediction and graph reasoning. For each family, it sorts representative methods into paradigms, and it then compiles the datasets and evaluation benchmarks that are commonly used.

It closes by naming the main open problem for each task:

  • weak structure–attribute encoding and few dedicated TAG generators in generation
  • immature evaluation and limited scalability in prediction
  • difficulty with complex relations and multi-hop inference in reasoning

The result is a unified reference for researchers who combine LLMs with graph learning.

Key points

  • Published in Acta Automatica Sinica, vol. 52, no. 8 (2026), pp. 1557–1592, DOI 10.16383/j.aas.c250499. The authors are from the Gaoling School of AI, Renmin University of China, and the corresponding author is WEI Zhe-Wei.
  • Generation is split into classic deep generative models (GraphRNN, NetGAN, GDSS) and LLM-based approaches. The LLM-based approaches cover both graph data augmentation (LLM4NG, GPT-GNN) and structure generation (LLM4GraphGen, GraphMaster).
  • Prediction methods are grouped by the role the LLM plays:
    • Predictor: InstructGLM, GraphGPT, LLaGA, GOFA
    • Enhancer: TAPE, KEA, ENGINE, SimTeG
    • Aligner: GLEM, ConGraT, G2P2
  • Reasoning is divided into two areas:
    • Classic graph reasoning: language-based methods (NLGraph, GraphWiz, GraphToken) and code-augmented methods (GraphTeam, GCoder, CodeGraph).
    • Knowledge-graph reasoning: ToG, RoG, G-Retriever, GNN-RAG and GraphRAG.
  • Background sections cover scaling laws, emergent abilities and prompting strategies (CoT, CoT-SC, ToT, GoT). The survey also catalogues datasets and benchmarks for all three task families.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages · Natural language processing

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.16383/j.aas.c250499

@inproceedings{2026,
  title = {{大模型驱动的文本属性图学习研究进展}},
  author = {郑艳萍 and 季嘉蕊 and 胡雨韦 and 魏哲巍},
  booktitle = {自动化学报 (Acta Automatica Sinica)},
  year = {2026},
  doi = {10.16383/j.aas.c250499},
  url = {https://doi.org/10.16383/j.aas.c250499}
}

References

255 references, 9 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Song X R, Lian J X, Huang H, Wu M Q, Jin H, Xie X. Friend recommendations with self-rescaling graph neural networks. In: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Washington, USA: Association for Computing Machinery, 2022. 3909−3919 find
  2. Xie Q Q, Zhu Y T, Huang J M, Du P, Nie J Y. Graph neural collaborative topic model for citation recommendation. ACM Transactions on Information Systems (TOIS), 2022, 40(3): Article No. 48 find
  3. Sun J S, Xu C J, Tang L M Y, Wang S Z, Lin C, Gong Y Y, et al. Think-on-graph: Deep and responsible reasoning of large language model on knowledge graph. In: Proceedings of the 12th International Conference on Learning Representations. Vienna, Austria: OpenReview.net, 2024. find
  4. Réau M, Renaud N, Xue L C, Bonvin A M J J. DeepRank-GNN: A graph neural network framework to learn patterns in protein-protein interfaces. Bioinformatics, 2023, 39(1): Article No. btac759 find
  5. Zhang S, Tong H H, Xu J J, Maciejewski R. Graph convolutional networks: Algorithms, applications and open challenges. In: Proceedings of the 7th International Conference on Computational Data and Social Networks. Shanghai, China: Springer, 2018. 79−91 find
  6. Veličković P, Cucurull G, Casanova A, Romero A, Liò P, Bengio Y. Graph attention networks. In: Proceedings of the 6th International Conference on Learning Representations. Vancouver, Canada: OpenReview.net, 2018. find
  7. Hamilton W L, Ying R, Leskovec J. Inductive representation learning on large graphs. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach, USA: Curran Associates Inc., 2017. 1025−1035 find our card
  8. Li Y H, Wang P S, Zhu X, Chen A C, Jiang H Y, Cai D, et al. GLBench: A comprehensive benchmark for graph with large language models. In: Proceedings of the 38th International Conference on Neural Information Processing Systems. Vancouver, Canada: Curran Associates Inc., 2024. Article No. 1340 find
  9. Hu W H, Fey M, Zitnik M, Dong Y X, Ren H Y, Liu B W, et al. Open graph benchmark: Datasets for machine learning on graphs. In: Proceedings of the 34th International Conference on Neural Information Processing Systems. Vancouver, Canada: Curran Associates Inc., 2020. find
  10. Sen P, Namata G, Bilgic M, Getoor L, Gallagher B, Eliassi-Rad T. Collective classification in network data. AI Magazine, 2008, 29(3): 93−106 find
  11. Miaschi A, Dell＇ Orletta F. Contextual and non-contextual word embeddings: An in-depth linguistic investigation. In: Proceedings of the 5th Workshop on Representation Learning for NLP. Virtual Event: Association for Computational Linguistics, 2020. 110−119 find
  12. Ethayarajh K. How contextual are contextualized word representations? Comparing the geometry of BERT, ELMo, and GPT-2 embeddings. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJC… find
  13. Touvron H, Martin L, Stone K, Albert P, Almahairi A, Babaei Y, et al. Llama 2: Open foundation and fine-tuned chat models. arXiv preprint arXiv: 2307.09288, 2023. find
  14. Chowdhery A, Narang S, Devlin J, Bosma M, Mishra G, Roberts A, et al. PaLM: Scaling language modeling with pathways. Journal of Machine Learning Research, 2023, 24(1): Article No. 240 find
  15. Li Y G, Liang F, Zhao L C, Cui Y F, Ouyang W L, Shao J, et al. Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm. In: Proceedings of the 10th International Conference on Learning Representations. Virtual Event: OpenReview.net, 2022. find
  16. Jin B W, Liu G, Han C, Jiang M, Ji H, Han J W. Large language models on graphs: A comprehensive survey. IEEE Transactions on Knowledge and Data Engineering, 2024, 36(12): 8622−8642 find
  17. Chen Z K, Mao H T, Li H, Jin W, Wen H Z, Wei X C, et al. Exploring the potential of large language models (LLMs) in learning on graphs. ACM SIGKDD Explorations Newsletter, 2023, 25(2): 42−61 find
  18. Li Z F, Gou Z X, Zhang X N, Liu Z Y, Li S R, Hu Y T, et al. TEG-DB: A comprehensive dataset and benchmark of textual-edge graphs. In: Proceedings of the 38th International Conference on Neural Information Processing Systems. Vancouver, Canada: Curran Associates Inc., 2024. find
  19. You J X, Ying R, Ren X, Hamilton W L, Leskovec J. GraphRNN: Generating realistic graphs with deep auto-regressive models. In: Proceedings of the 35th International Conference on Machine Learning. Stockholm, Sweden: PMLR, 2018. 5708−5717 find
  20. Samanta B, De A, Jana G, Chattaraj P K, Ganguly N, Rodriguez M G. NeVAE: A deep generative model for molecular graphs. In: Proceedings of the 33rd AAAI Conference on Artificial Intelligence. Honolulu, USA: AAAI, 2019. 1110−1117 find
  21. Luo Y Z, Yan K Q, Ji S W. GraphDF: A discrete flow model for molecular graph generation. In: Proceedings of the 38th International Conference on Machine Learning. Virtual Event: PMLR, 2021. 7192−7203 find
  22. Bojchevski A, Shchur O, Zügner D, Günnemann S. NetGAN: Generating graphs via random walks. In: Proceedings of the 35th International Conference on Machine Learning. Stockholm, Sweden: PMLR, 2018. 610−619 find
  23. Jo J, Lee S, Hwang S J. Score-based generative modeling of graphs via the system of stochastic differential equations. In: Proceedings of the 39th International Conference on Machine Learning. Baltimore, USA: PMLR, 2022. 10362−10383 find
  24. Zhang M Y, Cai Z A, Pan L, Hong F Z, Guo X Y, Yang L, et al. MotionDiffuse: Text-driven human motion generation with diffusion model. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2024, 46(6): 4115−4128 find
  25. Huang H, Sun L L, Du B W, Lv W F. Conditional diffusion based on discrete graph structures for molecular graph generation. In: Proceedings of the 37th AAAI Conference on Artificial Intelligence. Washington, USA: AAAI, 2023. 4302−4311 find
  26. Jung H, Park Y, Schmid L, Jo J, Lee D, Kim B, et al. Conditional synthesis of 3D molecules with time correction sampler. In: Proceedings of the 38th International Conference on Neural Information Processing Systems. Vancouver, Canada: Curran Associates Inc., 2024. Article No. 2417 find
  27. Dai H J, Nazi A, Li Y J, Dai B, Schuurmans D. Scalable deep generative modeling for sparse graphs. In: Proceedings of the 37th International Conference on Machine Learning. Virtual Event: PMLR, 2020. 2302−2312 find
  28. Yu J X, Ren Y X, Gong C H, Tan J Q, Li X, Zhang X C. Leveraging large language models for node generation in few-shot learning on text-attributed graphs. In: Proceedings of the 39th AAAI Conference on Artificial Intelligence. Philadelphia, USA: AAAI, 2025. 13087−13095 find
  29. Liu B, Qi G L. LLM-CG: Large language model-enhanced constraint graph for distantly supervised relation extraction. Neurocomputing, 2025, 655: Article No. 131426 find
  30. Zhang Z J, Wang X, Zhou H C, Yu Y, Zhang M M, Yang C, et al. Can large language models improve the adversarial robustness of graph neural networks? In: Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Toronto, Canada: Association for Computing Machinery, 2025. 20… find
  31. Hu Z N, Dong Y X, Wang K S, Chang K W, Sun Y Z. GPT-GNN: Generative pre-training of graph neural networks. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. Virtual Event: Association for Computing Machinery, 2020. 1857−1867 de Marzo G, Pietronero… — [arXiv:2312.06619](https://arxiv.org/abs/2312.06619) find
  32. Papachristou M, Yuan Y. Network formation and dynamics among multi-LLMs. arXiv preprint arXiv: 2402.10659, 2025. — [arXiv:2402.10659](https://arxiv.org/abs/2402.10659) find
  33. Yao Y, Wang X, Zhang Z Y, Qin Y J, Zhang Z W, Chu X, et al. Exploring the potential of large language models in graph generation. arXiv preprint arXiv: 2403.14358, 2024. — [arXiv:2403.14358](https://arxiv.org/abs/2403.14358) find
  34. Havrilla A, Alvarez-Melis D, Fusi N. IGDA: Interactive graph discovery through large language model agents. arXiv preprint arXiv: 2502.17189, 2025. — [arXiv:2502.17189](https://arxiv.org/abs/2502.17189) find
  35. Chang S, Chaszczewicz A, Wang E, Josifovska M, Pierson E, Leskovec J. LLMs generate structurally realistic social networks but overestimate political homophily. In: Proceedings of the 19th International AAAI Conference on Web and Social Media. Copenhagen, Denmark: AAAI, 2025. 341−371 find
  36. Ji J R, Lei R L, Bi J L, Wei Z W, Chen X, Lin Y K, et al. LLM-based multi-agent systems are scalable graph generative models. In: Proceedings of the Findings of the Association for Computational Linguistics. Vienna, Austria: Association for Computational Linguistics, 2025. 1492−1523 find
  37. Du E J, Li X K, Jin T, Zhang Z H, Li R H, Wang G R. Graph-Master: Automated graph synthesis via LLM agents in data limited environments. In: Proceedings of the 39th Conference on Neural Information Processing Systems. Mexico City, Mexico: Curran Associates Inc., 2025. find
  38. Wang Y, Rossi R A, Park N, Ahmed N K, Koutra D, Dernoncourt F, et al. Demystifying the power of large language models in graph generation. In: Proceedings of the Findings of the Association for Computational Linguistics: NAACL 2025. New Mexico, USA: Association for Computational Linguistics, 2025. 8… find
  39. Ye R S, Zhang C Q, Wang R H, Xu S Y, Zhang Y F. Language is all a graph needs. In: Proceedings of the Findings of the Association for Computational Linguistics: EACL 2024. St. Julian＇ s, Malta: Association for Computational Linguistics, 2024. 1955−1973 find
  40. Guo J Y, Du L, Liu H Y, Zhou M Y, He X Y, Han S. GPT4Graph: Can large language models understand graph structured data? An empirical evaluation and benchmarking. arXiv preprint arXiv: 2305.15066, 2023. find
  41. Zhao J N, Zhuo L, Shen Y K, Qu M, Liu K, Bronstein M, et al. GraphText: Graph reasoning in text space. arXiv preprint arXiv: 2310.01089, 2023. — [arXiv:2310.01089](https://arxiv.org/abs/2310.01089) find
  42. Lin T Q J, Yan P W, Song K S, Jiang Z R, Kang Y Y, Lin J, et al. LangGFM: A large language model alone can be a powerful graph foundation model. arXiv preprint arXiv: 2410.14961, 2024. — [arXiv:2410.14961](https://arxiv.org/abs/2410.14961) find
  43. Tang J B, Yang Y H, Wei W, Shi L, Su L X, Cheng S Q, et al. GraphGPT: Graph instruction tuning for large language models. In: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval. Washington, USA: Association for Computing Machinery, 2024. 4… find
  44. Chen R J, Zhao T, Jaiswal A K, Shah N, Wang Z Y. LLaGA: Large language and graph assistant. In: Proceedings of the 41st International Conference on Machine Learning. Vienna, Austria: PMLR, 2024. 7809−7823 find
  45. Kong L C, Feng J R, Liu H, Huang C S, Huang J X, Chen Y X, et al. GOFA: A generative one-for-all model for joint graph language modeling. In: Proceedings of the 13th International Conference on Learning Representations. Singapore: OpenReview.net, 2025. find
  46. Wang D, Zuo Y, Li F Z, Wu J J. LLMs as zero-shot graph learners: Alignment of GNN representations with LLM token embeddings. In: Proceedings of the 38th International Conference on Neural Information Processing Systems. Vancouver, Canada: Curran Associates Inc., 2024. Article No. 193 find
  47. He Z M, Zhu J, Qian S Y, Chai J, Koutra D. LinkGPT: Teaching large language models to predict missing links. arXiv preprint arXiv: 2406.04640, 2024. — [arXiv:2406.04640](https://arxiv.org/abs/2406.04640) find
  48. Zhang Z Y, Wang X, Zhang Z W, Li H Y, Qin Y J, Zhu W W. LLM4DyG: Can large language models solve spatial temporal problems on dynamic graphs? In: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Barcelona, Spain: Association for Computing Machinery, 2024. 4350−43… find
  49. Lei R L, Ji J R, Ding H P, Yi L, Wei Z W, Liu Y C, et al. Exploring the potential of large language models as predictors in dynamic text-attributed graphs. arXiv preprint arXiv: 2503.03258, 2025. — [arXiv:2503.03258](https://arxiv.org/abs/2503.03258) find
  50. Tang J B, Yang Y H, Wei W, Shi L, Xia L, Yin D W, et al. HiGPT: Heterogeneous graph language model. In: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Barcelona, Spain: Association for Computing Machinery, 2024. 2842−2853 find
  51. Chien E, Chang W C, Hsieh C J, Yu H F, Zhang J, Milenkovic O, et al. Node feature extraction by self-supervised multi-scale neighborhood prediction. In: Proceedings of the 10th International Conference on Learning Representations. Virtual Event: OpenReview.net, 2022. find
  52. Duan K Y, Liu Q, Chua T S, Yan S C, Ooi W T, Xie Q Z, et al. SimTeG: A frustratingly simple approach improves textual graph learning. arXiv preprint arXiv: 2308.02565, 2023. — [arXiv:2308.02565](https://arxiv.org/abs/2308.02565) find
  53. Gao H, Huang W X, Wu F G, Zhao J S, Zheng C W, Liu H P. LLM enhancers for GNNs: An analysis from the perspective of causal mechanism identification. In: Proceedings of the 42nd International Conference on Machine Learning. Vancouver, Canada: PMLR, 2025. 18585−18611 find
  54. Liu H, Feng J R, Kong L C, Liang N Y, Tao D C, Chen Y X, et al. One for all: Towards training one graph model for all classification tasks. In: Proceedings of the 12th International Conference on Learning Representations. Vienna, Austria: OpenReview.net, 2024. find
  55. Yang J H, Liu Z, Xiao S T, Li C Z, Lian D F, Agrawal S, et al. GraphFormers: GNN-nested Transformers for representation learning on textual graph. In: Proceedings of the 35th International Conference on Neural Information Processing Systems. Virtual Event: Curran Associates Inc., 2021. Article No. 2… find
  56. Jin B W, Zhang Y, Zhu Q, Han J W. Heterformer: Transformer-based deep node representation learning on heterogeneous text-rich networks. In: Proceedings of the 29th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Long Beach, USA: Association for Computing Machinery, 2023. 1020−1031 find
  57. Jin B W, Zhang Y, Meng Y, Han J W. Edgeformers: Graph-empowered Transformers for representation learning on textual-edge networks. In: Proceedings of the 11th International Conference on Learning Representations. Kigali, Rwanda: OpenReview.net, 2023. find
  58. Fang Y, Fan D Z, Ding S R, Liu N H, Tan Q Y. UniGLM: Training one unified language model for text-attributed graphs embedding. In: Proceedings of the 18th ACM International Conference on Web Search and Data Mining. Hannover, Germany: Association for Computing Machinery, 2025. 973−981 find
  59. Jin B W, Zhang W T, Zhang Y, Meng Y, Zhang X Y, Zhu Q, et al. PATTON: Language model pretraining on text-rich networks. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics. Toronto, Canada: Association for Computational Linguistics, 2023. 7005−7020 find
  60. Li Y H, Wang P S, Li Z X, Yu J X, Li J. ZeroG: Investigating cross-dataset zero-shot transferability in graphs. In: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Barcelona, Spain: Association for Computing Machinery, 2024. 1725−1735 find
  61. Xie H Y, Hu L J, Yu L, Huang T H, Li L F, Li M, et al. Efficient text-attributed graph learning through selective annotation and graph alignment. arXiv preprint arXiv: 2506.07168, 2025. — [arXiv:2506.07168](https://arxiv.org/abs/2506.07168) find
  62. Huang X W, Han K Q, Yang Y, Bao D Z, Tao Q J, Chai Z W, et al. Can GNN be good adapter for LLMs? In: Proceedings of the ACM Web Conference. Singapore: Association for Computing Machinery, 2024. 893−904 find
  63. Lu J L, Liu Y X, Zhang Y T, Fu Y. Scale-free graph-language models. In: Proceedings of the 13th International Conference on Learning Representations. Singapore: OpenReview.net, 2025. find
  64. Xia L H, Kao B, Huang C. OpenGraph: Towards open graph foundation models. In: Proceedings of the Findings of the Association for Computational Linguistics. Miami, USA: Association for Computational Linguistics, 2024. 2365−2379 find
  65. Zhu Y, Wang Y K, Shi H Z, Tang S L. Efficient tuning and inference for large language models on textual graphs. In: Proceedings of the 33rd International Joint Conference on Artificial Intelligence. Jeju, South Korea: ijcai.org, 2024. Article No. 634 find
  66. He X X, Bresson X, Laurent T, Perold A, LeCun Y, Hooi B. Harnessing explanations: LLM-to-LM interpreter for enhanced text-attributed graph representation learning. In: Proceedings of the 12th International Conference on Learning Representations. Vienna, Austria: OpenReview.net, 2024. find
  67. Pan B, Zhang Z, Zhang Y F, Hu Y T, Zhao L. Distilling large language models for text-attributed graph learning. In: Proceedings of the 33rd ACM International Conference on Information and Knowledge Management. Boise, USA: Association for Computing Machinery, 2024. 1836−1845 find
  68. Zhang Z H, Li X K, Li R H, Li Z J, Zhou B, Wang G R. Toward general and robust LLM-enhanced text-attributed graph learning. In: Proceedings of the International Conference on Multimedia Retrieval. Amsterdam, The Netherlands: Association for Computing Machinery, 2026. 1477−1485 find
  69. Zhao J N, Qu M, Li C Z, Yan H, Liu Q, Li R, et al. Learning on large-scale text-attributed graphs via variational inference. In: Proceedings of the 11th International Conference on Learning Representations. Kigali, Rwanda: OpenReview.net, 2023. find
  70. Brannon W, Kang W N J N, Fulay S, Jiang H, Roy B, Roy D, et al. ConGraT: Self-supervised contrastive pre training for joint graph and text embeddings. In: Proceedings of the Text-Graphs-17: Graph-based Methods for Natural Language Processing. Bangkok, Thailand: Association for Computational Linguist… find
  71. Wen Z H, Fang Y. Augmenting low-resource text classification with graph-grounded pre-training and prompting. In: Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval. Taipei, China: Association for Computing Machinery, 2023. 506−516 find
  72. Jiang X H, Shen Y H, Shi Z C, Xu C J, Li W, Li Z X, et al. Unlocking the power of large language models for entity alignment. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. Bangkok, Thailand: Association for Computational Linguistics, 2024. 7566−7583 find
  73. Roy A, Yan N, Mortazavi M. LLM-driven knowledge distillation for dynamic text-attributed graphs. arXiv preprint arXiv: 2502.10914, 2025. find
  74. Wang H, Feng S B, He T X, Tan Z X, Han X C, Tsvetkov Y. Can language models solve graph problems in natural language? In: Proceedings of the 37th International Conference on Neural Information Processing Systems. New Orleans, USA: Curran Associates Inc., 2023. Article No. 1345 find
  75. Fatemi B, Halcrow J, Perozzi B. Talk like a graph: Encoding graphs for large language models. In: Proceedings of the 12th International Conference on Learning Representations. Vienna, Austria: OpenReview.net, 2024. find
  76. Taylor A K, Cuturrufo A, Yathish V, Ma M D, Wang W. Are large-language models graph algorithmic reasoners? arXiv preprint arXiv: 2410.22597, 2024. — [arXiv:2410.22597](https://arxiv.org/abs/2410.22597) find
  77. Skianis K, Nikolentzos G, Vazirgiannis M. Graph reasoning with large language models via pseudo-code prompting. arXiv preprint arXiv: 2409.17906, 2024. find
  78. Hu Y W, Lei R L, Huang X Y, Wei Z W, Liu Y C. Scalable and accurate graph reasoning with LLM-based multi-agents. arXiv preprint arXiv: 2410.05130, 2025. — [arXiv:2410.05130](https://arxiv.org/abs/2410.05130) find
  79. Chai Z W, Zhang T J, Wu L, Han K Q, Hu X H, Huang X W, et al. GraphLLM: Boosting graph reasoning ability of large language model. IEEE Transactions on Big Data, 2026, 12(2): 475− 483 find
  80. Perozzi B, Fatemi B, Zelle D, Tsitsulin A, Kazemi M, Al-Rfou R, et al. Let your graph do the talking: Encoding structured data for LLMs. arXiv preprint arXiv: 2402.05862, 2024. — [arXiv:2402.05862](https://arxiv.org/abs/2402.05862) find
  81. Chen N, Li Y H, Tang J H, Li J. GraphWiz: An instruction-following language model for graph computational problems. In: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Barcelona, Spain: Association for Computing Machinery, 2024. 353−364 find
  82. Ouyang S, Hu Y L, Chen G, Liu Y. GUNDAM: Aligning large language models with graph understanding. arXiv preprint arXiv: 2409.20053, 2024. — [arXiv:2409.20053](https://arxiv.org/abs/2409.20053) find
  83. Wei Y B, Fu S, Jiang W S, Zhang Z J, Zeng Z X, Wu Q, et al. GITA: Graph to visual and textual integration for vision-language graph reasoning. In: Proceedings of the 38th International Conference on Neural Information Processing Systems. Vancouver, Canada: Curran Associates Inc., 2024. Article No. 2 find
  84. Li X, Chu Q Z, Chen Y B, Liu Y, Liu Y Q, Yu Z K, et al. GraphTeam: Facilitating large language model-based graph analysis via multi-agent collaboration. arXiv preprint arXiv: 2410.18032, 2025. — [arXiv:2410.18032](https://arxiv.org/abs/2410.18032) find
  85. Zhang Q F, Hong X B, Tang J H, Chen N, Li Y H, Li W Z, et al. GCoder: Improving large language model for generalized graph problem solving. arXiv preprint arXiv: 2410.19084, 2024. — [arXiv:2410.19084](https://arxiv.org/abs/2410.19084) find
  86. Gong C, Bian W R, Zhang Z J, Zheng W G. Pseudocode-injection magic: Enabling LLMs to tackle graph computational tasks. arXiv preprint arXiv: 2501.13731, 2025. — [arXiv:2501.13731](https://arxiv.org/abs/2501.13731) find
  87. Cai Q L, Wang Z W, Diao S Z, Kwok J, Song Y Q. Code-Graph: Enhancing graph reasoning of LLMs with code. arXiv preprint arXiv: 2408.13863, 2024. find
  88. Lukovnikov D, Fischer A, Lehmann J. Pretrained Transformers for simple question answering over knowledge graphs. In: Proceedings of the 18th International Semantic Web Conference on the Semantic Web. Auckland, New Zealand: Springer, 2019. 470−486 find
  89. Zhang Z Y, Han X, Liu Z Y, Jiang X, Sun M S, Liu Q. ERNIE: Enhanced language representation with informative entities. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Florence, Italy: Association for Computational Linguistics, 2019. 1441−1451 find
  90. Luo D, Su J D, Yu S S. A BERT-based approach with relation-aware attention for knowledge base question answering. In: Proceedings of the International Joint Conference on Neural Networks (IJCNN). Glasgow, UK: IEEE, 2020. 1−8 find
  91. Yasunaga M, Ren H Y, Bosselut A, Liang P, Leskovec J. QA-GNN: Reasoning with language models and knowledge graphs for question answering. In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Virtual Event: Asso… find
  92. Hu N, Wu Y K, Qi G L, Min D H, Chen J Y, Pan J Z, et al. An empirical study of pre-trained language models in simple knowledge graph question answering. World Wide Web, 2023, 26(5): 2855−2886 find
  93. Xu Y C, Zhu C G, Xu R C, Liu Y, Zeng M, Huang X D. Fusing context into knowledge graph for commonsense question answering. In: Proceedings of the Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021. Virtual Event: Association for Computational Linguistics, 2021. 1201− 1207 find
  94. Zhang M, Dai R F, Dong M, He T T. DRLK: Dynamic hierarchical reasoning with language model and knowledge graph for question answering. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing. Abu Dhabi, United Arab Emirates: Association for Computational Linguistics, 20… find
  95. Yan Y M, Li R M, Wang S R, Zhang H Z, Zan D G, Zhang F Z, et al. Large-scale relation learning for question answering over knowledge bases with pre-trained language models. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing. Punta Cana, Dominican Republic: Associat… find
  96. Hu Z N, Xu Y C, Yu W H, Wang S H, Yang Z Y, Zhu C G, et al. Empowering language models with knowledge graph reasoning for open-domain question answering. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing. Abu Dhabi, United Arab Emirates: Association for Computatio… find
  97. Zhang X K, Bosselut A, Yasunaga M, Ren H Y, Liang P, Manning C D, et al. GreaseLM: Graph REASoning enhanced language models for question answering. In: Proceedings of the 10th International Conference on Learning Representations. Virtual Event: OpenReview.net, 2022. find
  98. Jiang J H, Zhou K, Zhao X, Wen J R. UniKGQA: Unified retrieval and reasoning for solving multi-hop question answering over knowledge graph. In: Proceedings of the 11th International Conference on Learning Representations. Kigali, Rwanda: OpenReview.net, 2023. find
  99. Cao X, Liu Y. ReLMKG: Reasoning with pre-trained language models and knowledge graphs for complex question answering. Applied Intelligence, 2023, 53(10): 12032−12046 find
  100. Jiang J H, Zhou K, Dong Z C, Ye K M, Zhao X, Wen J R. StructGPT: A general framework for large language model to reason over structured data. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing. Singapore: Association for Computational Linguistics, 2023. 9237− 9251 find
  101. He X X, Tian Y J, Sun Y F, Chawla N V, Laurent T, LeCun Y, et al. G-Retriever: Retrieval-augmented generation for textual graph understanding and question answering. In: Proceedings of the 38th International Conference on Neural Information Processing Systems. Vancouver, Canada: Curran Associates In… find our card
  102. Six V, Dufraisse E, de Chalendar G. Decompositional reasoning for graph retrieval with large language models. arXiv preprint arXiv: 2506.13380, 2025. — [arXiv:2506.13380](https://arxiv.org/abs/2506.13380) find
  103. Luo L H, Li Y F, Haffari G, Pan S R. Reasoning on graphs: Faithful and interpretable large language model reasoning. In: Proceedings of the 12th International Conference on Learning Representations. Vienna, Austria: OpenReview.net, 2024. find
  104. Mavromatis C, Karypis G. GNN-RAG: Graph neural retrieval for efficient large language model reasoning on knowledge graphs. In: Proceedings of the Findings of the Association for Computational Linguistics. Vienna, Austria: Association for Computational Linguistics, 2025. 16682−16699 find
  105. Li M F, Miao S Q, Li P. Simple is effective: The roles of graphs and large language models in knowledge-graph-based retrieval-augmented generation. In: Proceedings of the 13th International Conference on Learning Representations. Singapore: Open-Review.net, 2025. find
  106. Ma S J, Xu C J, Jiang X H, Li M Z, Qu H R, Yang C H, et al. Think-on-graph 2.0: Deep and faithful large language model reasoning with knowledge-guided retrieval augmented generation. In: Proceedings of the 13th International Conference on Learning Representations. Singapore: OpenReview.net, 2025. find
  107. Chen L Y, Tong P R, Jin Z M, Sun Y, Ye J P, Xiong H. Plan-on-Graph: Self-correcting adaptive planning of large language model on knowledge graphs. In: Proceedings of the 38th International Conference on Neural Information Processing Systems. Vancouver, Canada: Curran Associates Inc., 2024. Article N… find
  108. Wen Y L, Wang Z F, Sun J M. MindMap: Knowledge graph prompting sparks graph of thoughts in large language models. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. Bangkok, Thailand: Association for Computational Linguistics, 2024. 10370−10388 find
  109. Deng Y H, Ye C C, Huang Z J, Ma M D, Kou Y W, Wang W. GraphVis: Boosting LLMs with visual knowledge graph integration. In: Proceedings of the 38th International Conference on Neural Information Processing Systems. Vancouver, Canada: Curran Associates Inc., 2024. Article No. 2155 find
  110. Edge D, Trinh H, Cheng N, Bradley J, Chao A, Mody A, et al. From local to global: A graph RAG approach to query-focused summarization. arXiv preprint arXiv: 2404.16130, 2025. find
  111. Liu Y, Lin X X, Shang Y M, Li Y X, Wang S, Cao Y N. Path-Mind: A retrieve-prioritize-reason framework for knowledge graph reasoning with large language models. In: Proceedings of the 40th AAAI Conference on Artificial Intelligence. Singapore: AAAI, 2026. 15386−15393 find
  112. Brown T B, Mann B, Ryder N, Subbiah M, Kaplan J, Dhariwal P, et al. Language models are few-shot learners. In: Proceedings of the 34th International Conference on Neural Information Processing Systems. Vancouver, Canada: Curran Associates Inc., 2020. Article No. 159 find
  113. Achiam J, Adler S, Agarwal S, Ahmad L, Akkaya I, Aleman F L, et al. GPT-4 technical report. arXiv preprint arXiv: 2303. 08774, 2024. find
  114. Kaplan J, McCandlish S, Henighan T, Brown T B, Chess B, Child R, et al. Scaling laws for neural language models. arXiv preprint arXiv: 2001.08361, 2020. find
  115. Wei J, Tay Y, Bommasani R, Raffel C, Zoph B, Borgeaud S, et al. Emergent abilities of large language models. Transactions on Machine Learning Research, 2022: 1−30 find our card
  116. Kojima T, Gu S S, Reid M, Matsuo Y, Iwasawa Y. Large language models are zero-shot reasoners. In: Proceedings of the 36th International Conference on Neural Information Processing Systems. New Orleans, USA: Curran Associates Inc., 2022. Article No. 1613 find our card
  117. Wang X Z, Wei J, Schuurmans D, Le Q V, Chi E H, Narang S, et al. Self-consistency improves chain of thought reasoning in language models. In: Proceedings of the 11th International Conference on Learning Representations. Kigali, Rwanda: OpenReview.net, 2023. find our card
  118. Xie Y X, Kawaguchi K, Zhao Y R, Zhao J X, Kan M Y, He J X, et al. Self-evaluation guided beam search for reasoning. In: Proceedings of the 37th International Conference on Neural Information Processing Systems. New Orleans, USA: Curran Associates Inc., 2023. find our card
  119. Long J Y. Large language model guided tree-of-thought. arXiv preprint arXiv: 2305.08291, 2023. find
  120. Yao S Y, Yu D, Zhao J, Shafran I, Griffiths T L, Cao Y, et al. Tree of thoughts: Deliberate problem solving with large language models. In: Proceedings of the 37th International Conference on Neural Information Processing Systems. New Orleans, USA: Curran Associates Inc., 2023. Article No. 517 find
  121. Besta M, Blach N, Kubicek A, Gerstenberger R, Podstawski M, Gianinazzi L, et al. Graph of thoughts: Solving elaborate problems with large language models. In: Proceedings of the 38th AAAI Conference on Artificial Intelligence. Vancouver, Canada: AAAI, 2024. 17682−17690 find
  122. Yin S K, Fu C Y, Zhao S R, Li K, Sun X, Xu T, et al. A survey on multimodal large language models. arXiv preprint arXiv: 2306.13549, 2024. find our card
  123. Liu H T, Li C Y, Wu Q Y, Lee Y J. Visual instruction tuning. In: Proceedings of the 37th International Conference on Neural Information Processing Systems. New Orleans, USA: Curran Associates Inc., 2023. Article No. 1516 find our card
  124. Huang R J, Li M Z, Yang D C, Shi J T, Chang X K, Ye Z H, et al. AudioGPT: Understanding and generating speech, music, sound, and talking head. In: Proceedings of the 38th AAAI Conference on Artificial Intelligence. Vancouver, Canada: AAAI, 2024. 23802−23804 find
  125. OpenAI. Video Generation Models as World Simulators, Technical Report, OpenAI, USA, 2024. find
  126. Bonifati A, Holubová I, Prat-Pérez A, Sakr S. Graph generators: State of the art and open challenges. ACM Computing Surveys (CSUR), 2021, 53(2): Article No. 53 find
  127. Eigenschink P, Reutterer T, Vamosi S, Vamosi R, Sun C, Kalcher K. Deep generative models for synthetic data: A survey. IEEE Access, 2023, 11: 47304−47320 find
  128. Zang C X, Wang F. MoFlow: An invertible flow model for generating molecular graphs. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. Virtual Event: Association for Computing Machinery, 2020. 617−626 find
  129. Vignac C, Krawczuk I, Siraudin A, Wang B H, Cevher V, Frossard P. DiGress: Discrete denoising diffusion for graph generation. In: Proceedings of the 11th International Conference on Learning Representations. Kigali, Rwanda: OpenReview.net, 2023. find
  130. Liao R J, Li Y J, Song Y, Wang S L, Hamilton W L, Duvenaud D, et al. Efficient graph generation with graph recurrent attention networks. In: Proceedings of the 33rd International Conference on Neural Information Processing Systems. Vancouver, Canada: Curran Associates Inc., 2019. Article No. 383 find
  131. Simonovsky M, Komodakis N. GraphVAE: Towards generation of small graphs using variational autoencoders. In: Proceedings of the 27th International Conference on Artificial Neural Networks. Rhodes, Greece: Springer, 2018. 412−422 find
  132. Grover A, Zweig A, Ermon S. Graphite: Iterative generative modeling of graphs. In: Proceedings of the 36th International Conference on Machine Learning. Long Beach, USA: PMLR, 2019. 2434−2444 find
  133. Geng Z J, Xie S F, Xia Y C, Wu L J, Qin T, Wang J, et al. De Novo molecular generation via connection-aware motif mining. In: Proceedings of the 11th International Conference on Learning Representations. Kigali, Rwanda: OpenReview.net, 2023. find
  134. Dinh L, Sohl-Dickstein J, Bengio S. Density estimation using real NVP. In: Proceedings of the 5th International Conference on Learning Representations. Toulon, France: OpenReview.net, 2017. find
  135. Rezende D J, Mohamed S. Variational inference with normalizing flows. In: Proceedings of the 32nd International Conference on Machine Learning. Lille, France: PMLR, 2015. 1530−1538 find
  136. Wang H W, Wang J, Wang J L, Zhao M, Zhang W N, Zhang F Z, et al. GraphGAN: Graph representation learning with generative adversarial nets. In: Proceedings of the 32nd AAAI Conference on Artificial Intelligence. New Orleans, USA: AAAI, 2018. 2508−2515 find
  137. Yang C, Zhuang P Y, Shi W H, Luu A, Li P. Conditional structure generation through graph variational generative adversarial nets. In: Proceedings of the 33rd International Conference on Neural Information Processing Systems. Vancouver, Canada: Curran Associates Inc., 2019. Article No. 120 find
  138. Yang L, Zhang Z L, Zhang W T, Hong S D. Score-based graph generative modeling with self-guided latent diffusion. In: Proceedings of the 11th International Conference on Learning Representations. Kigali, Rwanda: OpenReview.net, 2023. find
  139. Huang H, Sun L L, Du B W, Fu Y J, Lv W F. GraphGDP: Generative diffusion processes for permutation invariant graph generation. In: Proceedings of the IEEE International Conference on Data Mining (ICDM). Orlando, USA: IEEE, 2022. 201−210 find
  140. You J X, Liu B W, Ying Z T, Pande V S, Leskovec J. Graph convolutional policy network for goal-directed molecular graph generation. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems. Montréal, Canada: Curran Associates Inc., 2018. 6412−6422 find
  141. Popova M, Shvets M, Oliva J, Isayev O. MolecularRNN: Generating realistic molecular graphs with optimized properties. arXiv preprint arXiv: 1905.13372, 2019. — [arXiv:1905.13372](https://arxiv.org/abs/1905.13372) find
  142. Gupta S, Manchanda S, Bedathur S, Ranu S. TIGGER: Scalable generative modelling for temporal interaction graphs. In: Proceedings of the 36th AAAI Conference on Artificial Intelligence. Virtual Event: AAAI, 2022. 6819−6828 find
  143. Jang Y, Lee S, Ahn S. A simple and scalable representation for graph generation. In: Proceedings of the 12th International Conference on Learning Representations. Vienna, Austria: OpenReview.net, 2024. find
  144. Cohen-Karlik E, Rozenberg E, Freedman D. Overcoming order in autoregressive graph generation for molecule generation. arXiv preprint arXiv: 2402.03387, 2024. — [arXiv:2402.03387](https://arxiv.org/abs/2402.03387) find
  145. Zhang L M, Zhao L, Qin S, Pfoser D. TG-GAN: Deep generative models for continuously-time temporal graph generation. arXiv preprint arXiv: 2005.08323, 2020. — [arXiv:2005.08323](https://arxiv.org/abs/2005.08323) find
  146. Wang C, Xue N W, Pradhan S. A transition-based algorithm for AMR parsing. In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Denver, USA: Association for Computational Linguistics, 2015. 366−375 find
  147. Chen B, Sun L, Han X P. Sequence-to-action: End-to-end semantic graph generation for semantic parsing. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. Melbourne, Australia: Association for Computational Linguistics, 2018. 766−777 find
  148. Tan X W, Zhou Y X, Pergola G, He Y L. Set-aligning framework for auto-regressive event temporal graph generation. In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Mexico City, Mexico: Association for Comput… find
  149. Lu H, Wei Z Q, Wang X Z, Zhang K, Liu H. GraphGPT: A graph enhanced generative pretrained Transformer for conditioned molecular generation. International Journal of Molecular Sciences, 2023, 24(23): Article No. 16761 find
  150. Wang Y, Rossi R A, Park N, Chen H Y, Ahmed N K, Trivedi P, et al. A large-scale training paradigm for graph generative models. In: Proceedings of the 13th International Conference on Learning Representations. Singapore: OpenReview.net, 2025. find
  151. Tenorio V M, Zilberstein N, Segarra S, Marques A G. Graph guided diffusion: Unified guidance for conditional graph generation. arXiv preprint arXiv: 2505.19685, 2025. — [arXiv:2505.19685](https://arxiv.org/abs/2505.19685) find
  152. Li M F, Kreacic E, Potluru V K, Li P. GraphMaker: Can diffusion models generate large attributed graphs? arXiv preprint arXiv: 2310.13833, 2024. — [arXiv:2310.13833](https://arxiv.org/abs/2310.13833) find
  153. Zhang D C, Yang M L, Ying R, Lauw H W. Text-attributed graph representation learning: Methods, applications, and challenges. In: Proceedings of the ACM Web Conference. Singapore: Association for Computing Machinery, 2024. 1298−1301 find
  154. Wang L Y, Wang Y, Ni B, Zhao Y, Wang H Y, Ma Y, et al. SAVE-TAG: Semantic-aware vicinal risk minimization for long-tailed text-attributed graphs. arXiv preprint arXiv: 2410.16882, 2025. — [arXiv:2410.16882](https://arxiv.org/abs/2410.16882) find
  155. Gao C, Lan X C, Li N, Yuan Y, Ding J T, Zhou Z L, et al. Large language models empowered agent-based modeling and simulation: A survey and perspectives. Humanities and Social Sciences Communications, 2024, 11(1): Article No. 1259 find
  156. Park J S, O＇ Brien J, Cai C J, Morris M R, Liang P, Bernstein M S. Generative agents: Interactive simulacra of human behavior. In: Proceedings of the 36th Annual ACM Symposium on User Interface Software and Technology. San Francisco, USA: Association for Computing Machinery, 2023. Article No. 2 find
  157. Li N, Gao C, Li M Y, Li Y, Liao Q M. EconAgent: Large language model-empowered agents for simulating macroeconomic activities. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics. Bangkok, Thailand: Association for Computational Linguistics, 2024. 15523−15536 find
  158. Mou X Y, Ding X W, He Q, Wang L, Liang J C, Zhang X N, et al. From individual to society: A survey on social simulation driven by large language model-based agents. ACM Computing Surveys, 2026, 58(11): Article No. 280 find
  159. Barabási A L, Albert R. Emergence of scaling in random networks. Science, 1999, 286(5439): 509−512 find
  160. Kleinberg J M, Kumar R, Raghavan P, Rajagopalan S, Tomkins A S. The web as a graph: Measurements, models, and methods. In: Proceedings of the 5th Annual International Conference on Computing and Combinatorics. Tokyo, Japan: Springer, 1999. 1−17 find
  161. Ioannides Y M. Random graphs and social networks: An economics perspective [Online], available: https://www.researchg-ate.net/publication/24137958, July 21, 2026 ↗
  162. Gao C, Lan X C, Lu Z H, Mao J Z, Piao J, Wang H D, et al. S3: Social-network simulation system with large language model-empowered agents. arXiv preprint arXiv: 2307.14984, 2025. — [arXiv:2307.14984](https://arxiv.org/abs/2307.14984) find
  163. Mou X Y, Wei Z Y, Huang X J. Unveiling the truth and facilitating change: Towards agent-based large-scale social movement simulation. In: Proceedings of the Findings of the Association for Computational Linguistics. Bangkok, Thailand: Association for Computational Linguistics, 2024. 4789−4809 find
  164. Yang Z Y, Zhang Z B, Zheng Z R, Jiang Y X, Gan Z Y, Wang Z Y, et al. OASIS: Open agent social interaction simulations with one million agents. arXiv preprint arXiv: 2411.11581, 2025. — [arXiv:2411.11581](https://arxiv.org/abs/2411.11581) find
  165. Rossetti G, Stella M, Cazabet R, Abramski K, Cau E, Citraro S, et al. Y social: An LLM-powered social media digital twin. arXiv preprint arXiv: 2408.00818, 2024. — [arXiv:2408.00818](https://arxiv.org/abs/2408.00818) find
  166. Zhang X Q, Chen X Y, Liu Y H, Wang J Z, Hu Z X, Yan R. A large scale time-aware agents simulation for influencer selection in digital advertising campaigns. arXiv preprint arXiv: 2411.01143, 2024. — [arXiv:2411.01143](https://arxiv.org/abs/2411.01143) find
  167. Liu Y H, Song Z R, Zhang J T, Zhang X Q, Chen X Y, Yan R. The stepwise deception: Simulating the evolution from true news to fake news with LLM agents. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing. Suzhou, China: Association for Computational Linguistics, 202… find
  168. Ji J R, Li Y, Liu H T, Du Z C, Wei Z W, Qi Q, et al. SRAP-agent: Simulating and optimizing scarce resource allocation policy with LLM-based agent. In: Proceedings of the Findings of the Association for Computational Linguistics: EMNLP. Miami, USA: Association for Computational Linguistics, 2024. 267… find
  169. Leskovec J, Chakrabarti D, Kleinberg J, Faloutsos C, Ghahramani Z. Kronecker graphs: An approach to modeling networks. The Journal of Machine Learning Research, 2010, 11: 985−1042 find
  170. Park H, Kim M S. TrillionG: A trillion-scale synthetic graph generator using a recursive vector model. In: Proceedings of the ACM International Conference on Management of Data. Chicago, USA: Association for Computing Machinery, 2017. 913−928 find
  171. Gutfraind A, Safro I, Meyers L A. Multiscale network generation. In: Proceedings of the 18th International Conference on Information Fusion. Washington, USA: IEEE, 2015. 158−165 find
  172. Gao C, Zheng Y, Li N, Li Y F, Qin Y R, Piao J H, et al. A survey of graph neural networks for recommender systems: Challenges, methods, and directions. ACM Transactions on Recommender Systems, 2023, 1(1): Article No. 3 find
  173. Ebrat D, Paradalis E, Rueda L. Lusifer: LLM-based user simulated feedback environment for online recommender systems. In: Proceedings of the 4th International Conference on Computing and Machine Intelligence (ICMI). MI, USA: IEEE, 2025. 1−6 find
  174. Corecco N, Piatti G, Lanzendörfer L A, Fan F X, Wattenhofer R. SUBER: An RL environment with simulated human behavior for recommender systems. In: Proceedings of the 27th European Conference on Artificial Intelligence. Santiago de Compostela, Spain: IOS Press, 2024. 2210−2217 find
  175. Wang L, Zhang J S, Yang H, Chen Z Y, Tang J K, Zhang Z Y, et al. User behavior simulation with large language model-based agents. ACM Transactions on Information Systems, 2025, 43(2): Article No. 55 find
  176. Chen L Y, Dai Q Y, Zhang Z Y, Feng X Y, Zhang M Y, Tang P C, et al. RecUserSim: A realistic and diverse user simulator for evaluating conversational recommender systems. In: Proceedings of the Companion Proceedings of the ACM on Web Conference. Sydney, Australia: Association for Computing Machinery,… find
  177. Zhang A, Chen Y X, Sheng L H, Wang X, Chua T S. On generative agents in recommendation. In: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval. Washington, USA: Association for Computing Machinery, 2024. 1807−1817 find
  178. Ying C X, Cai T L, Luo S J, Zheng S X, Ke G L, He D, et al. Do Transformers really perform bad for graph representation? In: Proceedings of the 35th International Conference on Neural Information Processing Systems. Virtual Event: Curran Associates Inc., 2021. Article No. 2212 find
  179. Yang C D, Liu H R, Wang D X, Zhang Z Q, Yang C, Shi C. FLAG: Fraud detection with LLM-enhanced graph neural network. In: Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Toronto, Canada: Association for Computing Machinery, 2025. 5150−5160 find
  180. Huang T R, Wang Y L, Li Q T, He C L, Gao J L. Can LLMs find fraudsters? Multi-level LLM enhanced graph fraud detection. In: Proceedings of the 33rd ACM International Conference on Multimedia. Dublin, Ireland: Association for Computing Machinery, 2025. 1530−1538 find
  181. Xue C, Lu Y W, Yang C, Xing J M. RecMind: LLM-enhanced graph neural networks for personalized consumer recommendations. In: Proceedings of the IEEE International Conference on Consumer Electronics (ICCE). Dubai, United Arab Emirates: IEEE, 2026. 1−6 find
  182. Wei W, Ren X B, Tang J B, Wang Q Y, Su L X, Cheng S Q, et al. LLMRec: Large language models with graph augmentation for recommendation. In: Proceedings of the 17th ACM International Conference on Web Search and Data Mining. Merida, Mexico: Association for Computing Machinery, 2024. 806−815 find
  183. He X N, Deng K, Wang X, Li Y, Zhang Y D, Wang M. Light-GCN: Simplifying and powering graph convolution network for recommendation. In: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. Virtual Event: Association for Computing Machinery,… find
  184. Wu L K, Qiu Z P, Zheng Z, Zhu H S, Chen E H. Exploring large language model for graph data understanding in online job recommendations. In: Proceedings of the 38th AAAI Conference on Artificial Intelligence. Vancouver, Canada: AAAI, 2024. 9178−9186 find
  185. Guo T, Hauptman E. Fine-tuning large language models for stock return prediction using newsflow. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing: Industry Track. Miami, USA: Association for Computational Linguistics, 2024. 1028−1045 find
  186. Xu Z Y, Liu Y, Wang Y C, Bao R H, Harimoto K, Sun X. Modeling interactions between stocks using LLM-enhanced graphs for volume prediction. In: Proceedings of the 9th Financial Technology and Natural Language Processing (FinNLP), the 6th Financial Narrative Processing (FNP), and the 1st Workshop on L… find
  187. Liu C, Wu B. Evaluating large language models on graphs: Performance insights and comparative analysis. arXiv preprint arXiv: 2308.11224, 2023. — [arXiv:2308.11224](https://arxiv.org/abs/2308.11224) find
  188. Himsolt M. GML: A Portable Graph File Format, Technical Report, Universität Passau, Germany, 1997. find
  189. Brandes U, Eiglsperger M, Lerner J, Pich C. Graph markup language (GraphML) [Online], available: https://cs.brown.edu/people/rtamassi/gdhandbook/chapters/graphml.pdf, July 21, 2026 ↗
  190. Liu N F, Lin K, Hewitt J, Paranjape A, Bevilacqua M, Petroni F, et al. Lost in the middle: How language models use long contexts. In: Proceedings of the Transactions of the Association for Computational Linguistics. Cambridge, USA: MIT Press, 2024. 157−173 find our card
  191. Luo Z H, Song X R, Huang H, Lian J X, Zhang C H, Jiang J Q, et al. GraphInstruct: Empowering large language models with graph understanding and reasoning capability. arXiv preprint arXiv: 2403.04483, 2025. — [arXiv:2403.04483](https://arxiv.org/abs/2403.04483) find
  192. Gansner E R, North S C. An open graph visualization system and its applications to software engineering. Software: Practice and Experience, 2000, 30(11): 1203−1233 find
  193. Tosi S. Matplotlib for Python Developers: Build Remarkable Publication Quality Plots the Easy Way. Birmingham: Packt Publishing, 2009. find
  194. Zhao H T, Liu S C, Ma C, Xu H N, Fu J, Deng Z H, et al. GIMLET: A unified graph-text model for instruction-based molecule zero-shot learning. In: Proceedings of the 37th International Conference on Neural Information Processing Systems. New Orleans, USA: Curran Associates Inc., 2023. Article No. 257 find
  195. Feng Y C, Zhou L, Ma C, Zheng Y K, He R K, Li Y X. Knowledge graph-based thought: A knowledge graph-enhanced LLM framework for pan-cancer question answering. GigaScience, 2025, 14: Article No. giae082 find
  196. He J L, Guo Y Q, Lam L K, Leung W, He L X, Jiang Y A, et al. OpenTCM: A GraphRAG-empowered LLM-based system for traditional Chinese medicine knowledge retrieval and diagnosis. arXiv preprint arXiv: 2504.20118, 2025. — [arXiv:2504.20118](https://arxiv.org/abs/2504.20118) find
  197. Wang S J, Fan W Q, Feng Y, Lin S R, Ma X Y, Wang S Q, et al. Knowledge graph retrieval-augmented generation for LLM-based recommendation. In: Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics. Vienna, Austria: Association for Computational Linguistics, 2025. 271… find
  198. Qiu Z C, Luo L H, Pan S R, Liew A W C. Unveiling user preferences: A knowledge graph and LLM-driven approach for conversational recommendation. arXiv preprint arXiv: 2411.14459, 2024. — [arXiv:2411.14459](https://arxiv.org/abs/2411.14459) find
  199. Zhu Y C, Steck H, Liang D W, He Y H, Kallus N, Li J D. LLM-based conversational recommendation agents with collaborative verbalized experience. In: Proceedings of the Findings of the Association for Computational Linguistics. Suzhou, China: Association for Computational Linguistics, 2025. 2207−2220 find
  200. Pirmorad E. Exploring the in-context learning capabilities of LLMs for money laundering detection in financial graphs. In: Proceedings of the IEEE International Conference on Data Mining Workshops (ICDMW). Washington, USA: IEEE, 2025. 174−177 find
  201. He P L, Meng H N. A fast discovery model for production financial risk using large language model and knowledge graph. Journal of Circuits, Systems and Computers, 2025, 34(9): Article No. 2550206 find
  202. Khanvilkar K, Kommuru K. Regulatory graphs and GenAI for real-time transaction monitoring and compliance explanation in banking. arXiv preprint arXiv: 2506.01093, 2025. — [arXiv:2506.01093](https://arxiv.org/abs/2506.01093) find
  203. Peng J, Ji J R, Lei R L, Wei Z W, Liu Y C, Hong C T. GDGB: A benchmark for generative dynamic text-attributed graph learning. arXiv preprint arXiv: 2507.03267, 2026. — [arXiv:2507.03267](https://arxiv.org/abs/2507.03267) find
  204. Ren R Y, Qiu P, Qu Y Q, Liu J, Zhao W X, Wu H, et al. BASES: Large-scale web search user simulation with large language model based agents. In: Proceedings of the Findings of the Association for Computational Linguistics. Miami, USA: Association for Computational Linguistics, 2024. 902−917 find
  205. Zhang X Q, Liu Y H, Wang J Z, Hu Z X, Chen X Y, Yan R. SAGraph: A large-scale social graph dataset with comprehensive context for influencer selection in marketing. In: Proceedings of the 48th International ACM SIGIR Conference on Research and Development in Information Retrieval. Padua, Italy: Asso… find
  206. Mou X Y, Qian C, Liu W, Yan L, Hu Y, Huang X J, et al. EcoLANG: Efficient and effective agent communication language induction for social simulation. In: Proceedings of the Findings of the Association for Computational Linguistics. Suzhou, China: Association for Computational Linguistics, 2025. 5287… find
  207. Chang R C, Rao A, Zhong Q K, Wojcieszak M, Lerman K. \#RoeOverturned: Twitter dataset on the abortion rights controversy. In: Proceedings of the 17th International AAAI Conference on Web and Social Media. Limassol, Cyprus: AAAI, 2023. 997−1005 find
  208. Harper F M, Konstan J A. The MovieLens datasets: History and context. ACM Transactions on Interactive Intelligent Systems (TiiS), 2016, 5(4): Article No. 19 find
  209. Huang X, Lian J X, Lei Y X, Yao J, Lian D F, Xie X. Recommender AI agent: Integrating large language models for interactive recommendations. ACM Transactions on Information Systems, 2025, 43(4): Article No. 96 find
  210. Zhang J J, Hou Y P, Xie R B, Sun W Q, McAuley J J, Zhao W X, et al. AgentCF: Collaborative learning with autonomous language agents for recommender systems. In: Proceedings of the ACM Web Conference. Singapore: Association for Computing Machinery, 2024. 3679−3689 find
  211. Hou Y P, Li J C, He Z K, Yan A, Chen X S, McAuley J. Bridging language and items for retrieval and recommendation. arXiv preprint arXiv: 2403.03952, 2024. — [arXiv:2403.03952](https://arxiv.org/abs/2403.03952) find
  212. Liu Y J, Liu W, Gu X Y, Rui Y, He X D, Zhang Y D. LMAgent: A large-scale multimodal agents society for multi-user simulation. IEEE Transactions on Multimedia, DOI: 10.1109/TMM.2026.3651078 Kang W C, McAuley J. Self-attentive sequential recommendation. In: Proceedings of the IEEE International Confer… — [doi:10.1109/tmm.2026.3651078](https://doi.org/10.1109/tmm.2026.3651078) find
  213. Cantador I, Brusilovsky P, Kuflik T. Second workshop on information heterogeneity and fusion in recommender systems (HetRec2011). In: Proceedings of the 5th ACM Conference on Recommender Systems. Chicago, USA: Association for Computing Machinery, 2011. 387−388 find
  214. Ozsoy M G. Multilingual prompts in LLM-based recommenders: Performance across languages. arXiv preprint arXiv: 2409.07604, 2024. — [arXiv:2409.07604](https://arxiv.org/abs/2409.07604) find
  215. Liao J Y, Li S H, Yang Z Y, Wu J C, Yuan Y C, Wang X, et al. LLaRA: Large language-recommendation assistant. In: Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval. Washington, USA: Association for Computing Machinery, 2024. 1785−1795 find
  216. Zheng K, Sun Q F, Xu C, Yu P, Guo Q W. Towards a unified paradigm: Integrating recommendation systems as a new language in large models. arXiv preprint arXiv: 2412.16933, 2024. — [arXiv:2412.16933](https://arxiv.org/abs/2412.16933) find
  217. Jiang B, Zhang Z Y, Lin D D, Tang J, Luo B. Semi-supervised learning with graph learning-convolutional networks. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Long Beach, USA: IEEE, 2019. 11305−11312 find
  218. Morris C, Ritzert M, Fey M, Hamilton W L, Lenssen J E, Rattan G, et al. Weisfeiler and leman go neural: Higher-order graph neural networks. In: Proceedings of the 33rd AAAI Conference on Artificial Intelligence. Honolulu, USA: AAAI, 2019. 4602−4609 find
  219. Thompson R, Knyazev B, Ghalebi E, Kim J, Taylor G W. On evaluation metrics for graph generative models. In: Proceedings of the 10th International Conference on Learning Representations. Virtual Event: OpenReview.net, 2022. find
  220. Wang C E, Kantarcioglu M. Graph generative models evaluation with masked autoencoder. In: Proceedings of the Trends and Applications in Knowledge Discovery and Data Mining. Sydney, Australia: Springer, 2025. 137−148 find
  221. Heusel M, Ramsauer H, Unterthiner T, Nessler B, Hochreiter S. GANs trained by a two time-scale update rule converge to a local Nash equilibrium. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach, USA: Curran Associates Inc., 2017. 6629−6640 find
  222. Hosseini R, Simini F, Vishwanath V, Willett R, Hoffmann H. Quality measures for dynamic graph generative models. In: Proceedings of the 13th International Conference on Learning Representations. Singapore: OpenReview.net, 2025. find
  223. Yoon M, Wu Y, Palowitch J, Perozzi B, Salakhutdinov R. Graph generative model for benchmarking graph neural networks. In: Proceedings of the 40th International Conference on Machine Learning. Honolulu, USA: PMLR, 2023. 40175−40198 find
  224. Kipf T N, Welling M. Variational graph auto-encoders. arXiv preprint arXiv: 1611.07308, 2016. — [arXiv:1611.07308](https://arxiv.org/abs/1611.07308) find
  225. Yan H, Li C Z, Long R S, Yan C, Zhao J N, Zhuang W W, et al. A comprehensive study on text-attributed graphs: Benchmarking and rethinking. In: Proceedings of the 37th International Conference on Neural Information Processing Systems. New Orleans, USA: Curran Associates Inc., 2023. Article No. 755 find
  226. Berant J, Chou A, Frostig R, Liang P. Semantic parsing on freebase from question-answer pairs. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing. Seattle, USA: Association for Computational Linguistics, 2013. 1533−1544 find
  227. Bordes A, Usunier N, Chopra S, Weston J. Large-scale simple question answering with memory networks. arXiv preprint arXiv: 1506.02075, 2015. find
  228. Bao J W, Duan N, Yan Z, Zhou M, Zhao T J. Constraint-based question answering with knowledge graph. In: Proceedings of the 26th International Conference on Computational Linguistics: Technical Papers. Osaka, Japan: The COLING 2016 Organizing Committee, 2016. 2503−2514 find
  229. Su Y, Sun H, Sadler B M, Srivatsa M, Gür I, Yan Z H, et al. On generating characteristic-rich question sets for QA evaluation. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing. Austin, USA: Association for Computational Linguistics, 2016. 562−572 find
  230. Yih W T, Richardson M, Meek C, Chang M W, Suh J. The value of semantic parse labeling for knowledge base question answering. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. Berlin, Germany: Association for Computational Linguistics, 2016. 201−206 find
  231. Serban I V, García-Durán A, Gulcehre C, Ahn S, Chandar S, Courville A C, et al. Generating factoid questions with recurrent neural networks: The 30M factoid question-answer corpus. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. Berlin, Germany: Associati… find
  232. Diefenbach D, Tanon T P, Singh K D, Maret P. Question answering benchmarks for Wikidata. In: Proceedings of the Posters & Demonstrations and Industry Tracks Co-located With 16th International Semantic Web Conference (ISWC 2017). find
  233. Vienna, Austria: CEUR-WS.org, 2017. find
  234. Trivedi P, Maheshwari G, Dubey M, Lehmann J. LC-QuAD: A corpus for complex question answering over knowledge graphs. In: Proceedings of the 16th International Semantic Web Conference on the Semantic Web. Vienna, Austria: Springer, 2017. 210−218 find
  235. Talmor A, Berant J. The web as a knowledge-base for answering complex questions. In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. New Orleans, Louisiana: Association for Computational Linguistics, 2018. 641… find
  236. Usbeck R, Gusmita R H, Ngomo A N, Saleem M. 9th challenge on question answering over linked data (QALD-9) (invited paper). In: Proceedings of the 4th Workshop on Semantic Deep Learning (SemDeep-4) and NLIWoD4: Natural Language Interfaces for the Web of Data (NLIWOD-4) and 9th Question Answering Over… find
  237. Monterey, USA: CEUR-WS.org, 2018. 58−64 find
  238. Zhou M T, Huang M L, Zhu X Y. An interpretable reasoning network for multi-relation question answering. In: Proceedings of the 27th International Conference on Computational Linguistics. Santa Fe, USA: Association for Computational Linguistics, 2018. 2010−2022 find
  239. Zhang Y Y, Dai H J, Kozareva Z, Smola A J, Song L. Variational reasoning for question answering with knowledge graph. In: Proceedings of the 32nd AAAI Conference on Artificial Intelligence. New Orleans, USA: AAAI, 2018. 6069−6076 find
  240. Azmy M, Shi P, Lin J, Ilyas I F. Farewell freebase: Migrating the SimpleQuestions dataset to DBpedia. In: Proceedings of the 27th International Conference on Computational Linguistics. Santa Fe, USA: Association for Computational Linguistics, 2018. 2093−2103 find
  241. Dubey M, Banerjee D, Abdelkawi A, Lehmann J. LC-QuAD 2.0: A large dataset for complex question answering over Wikidata and DBpedia. In: Proceedings of the 18th International Semantic Web Conference on the Semantic Web. Auckland, New Zealand: Springer, 2019. 69−78 find
  242. Jiang K, Wu D K, Jiang H. FreebaseQA: A new factoid QA data set matching trivia-style question-answer pairs with freebase. In: Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Minneapolis, Minnesota: Associatio… find
  243. Costa T S, Gottschalk S, Demidova E. Event-QA: A dataset for event-centric question answering over knowledge graphs. In: Proceedings of the 29th ACM International Conference on Information & Knowledge Management. Virtual Event: Association for Computing Machinery, 2020. 3157−3164 find
  244. Gu Y, Kase S, Vanni M, Sadler B M, Liang P, Yan X F, et al. Beyond I.I.D.: Three levels of generalization for question answering on knowledge bases. In: Proceedings of the Web Conference. Ljubljana, Slovenia: Association for Computing Machinery, 2021. 3477−3488 find
  245. Tang J H, Zhang Q F, Li Y H, Chen N, Li J. GraphArena: Evaluating and exploring large language models on graph computation. In: Proceedings of the 13th International Conference on Learning Representations. Singapore: ICLR, 2025. find
  246. Chen X H, He J X, Han X, Liu L P. Efficient and degree-guided graph generation via discrete diffusion modeling. In: Proceedings of the 40th International Conference on Machine Learning. Honolulu, USA: PMLR, 2023. 4585−4610 find
  247. O＇ Bray L, Horn M, Rieck B, Borgwardt K M. Evaluation metrics for graph generative models: Problems, pitfalls, and practical solutions. In: Proceedings of the 10th International Conference on Learning Representations. Virtual Event: OpenReview.net, 2022. find
  248. Li A G, Yu L. Summary factual inconsistency detection based on LLMs enhanced by universal information extraction. In: Proceedings of the Findings of the Association for Computational Linguistics. Vienna, Austria: Association for Computational Linguistics, 2025. 25450−25465 find
  249. Zhang L, Song D D, Wu Z J, Tian Y H, Zhou C Z, Xu J, et al. Detecting hallucination in large language models through deep internal representation analysis. In: Proceedings of the 34th International Joint Conference on Artificial Intelligence. Montreal, Canada: ijcai.org, 2025. 8357−8365 find
  250. Zhang Y, Zhao Y Y, Li Z Q, Cheng X Q, Wang Y, Kotevska O, et al. A survey on privacy in graph neural networks: Attacks, preservation, and applications. IEEE Transactions on Knowledge and Data Engineering, 2024, 36(12): 7497−7515 find
  251. Sheng Z A, Guo W Y, Shao Y X, Zhang W T, Cui B. LLMs are noisy oracles! LLM-based noise-aware graph active learning for node classification. In: Proceedings of the 31st ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2. Toronto, Canada: Association for Computing Machinery, 2025. 2526−… find
  252. Huang J, Zhang X J, Mei Q Z, Ma J Q. Can LLMs effectively leverage graph structural information through prompts, and why? arXiv preprint arXiv: 2309.16595, 2024. — [arXiv:2309.16595](https://arxiv.org/abs/2309.16595) find
  253. 郑艳萍 中国人民大学高瓴人工智能 学院博士后. 2024 年获得中国人民大 学高瓴人工智能学院博士学位. 主要 研究方向为图机器学习. E-mail: zhengyanping@ruc.edu.cn (ZHENG Yan-Ping Postdoctor at the Gaoling School of Artificial Intelligence, Renmin University of China. She received her Ph.D. degree from Gaoling School of Artificial Intelligence, Renmin University… find
  254. 季嘉蕊 中国人民大学高瓴人工智能 学院博士研究生. 2023 年获得同济大 学学士学位. 主要研究方向为大语言 模型, 图学习. E-mail: jijiarui@ruc.edu.cn (JI Jia-Rui Ph.D. candidate at the Gaoling School of Artificial Intelligence, Renmin University of China. She received her bachelor degree from Tongji University in 2023. Her research interests include large… find
  255. 胡雨韦 中国人民大学高瓴人工智能 学院博士研究生. 2024 年获得中国人 民大学学士学位. 主要研究方向为大 语言模型, 图学习. E-mail: huyuweiyisui@ruc.edu.cn (HU Yu-Wei Ph.D. candidate at the Gaoling School of Artificial Intelligence, Renmin University of China. He received his bachelor degree from Renmin University of China in 2024. His research interests… find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/zheng-2026-recent-advances-text/