{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,29]],"date-time":"2026-06-29T12:11:20Z","timestamp":1782735080628,"version":"3.54.5"},"reference-count":41,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62322606"],"award-info":[{"award-number":["62322606"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang NSF","award":["LR22F020005"],"award-info":[{"award-number":["LR22F020005"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Big Data"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tbdata.2025.3627488","type":"journal-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T18:04:23Z","timestamp":1761847463000},"page":"475-483","source":"Crossref","is-referenced-by-count":13,"title":["GraphLLM: Boosting Graph Reasoning Ability of Large Language Model"],"prefix":"10.1109","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1376-5101","authenticated-orcid":false,"given":"Ziwei","family":"Chai","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9287-9555","authenticated-orcid":false,"given":"Tianjie","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liang","family":"Wu","sequence":"additional","affiliation":[{"name":"State Grid Zhejiang Electric Power Supply Company Ltd., Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-1389-1291","authenticated-orcid":false,"given":"Kaiqiao","family":"Han","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohai","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Washington, Seattle, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuanwen","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5058-4417","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Graph inductive biases in transformers without message passing","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ma"},{"key":"ref2","first-page":"3844","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Defferrard"},{"key":"ref3","article-title":"Language models are few-shot learners","author":"Brown","year":"2020"},{"key":"ref4","article-title":"GPT4Graph: Can large language models understand graph structured data? An empirical evaluation and benchmarking","author":"Guo","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1201\/b15385-19"},{"key":"ref6","article-title":"Explanations as features: LLM-based features for text-attributed graphs","author":"He","year":"2023"},{"key":"ref7","article-title":"Exploring the potential of large language models (LLMs) in learning on graphs","author":"Chen","year":"2023"},{"key":"ref8","article-title":"Lost in the middle: How language models use long contexts","author":"Liu","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.353"},{"key":"ref10","article-title":"Can language models solve graph problems in natural language?","author":"Wang","year":"2023"},{"key":"ref11","article-title":"Natural language is all a graph needs","author":"Ye","year":"2023"},{"key":"ref12","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref13","first-page":"11803","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hu"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.243"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"ref16","article-title":"LLaMA-Adapter: Efficient fine-tuning of language models with zero-init attention","author":"Zhang","year":"2023"},{"key":"ref17","article-title":"mPLUG-Owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023"},{"key":"ref18","article-title":"LLaMA-Adapter V2: Parameter-efficient visual instruction model","author":"Gao","year":"2023"},{"key":"ref19","article-title":"What matters in training a GPT4-style language model with multimodal inputs?","author":"Zeng","year":"2023"},{"key":"ref20","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref21","article-title":"Training language models to follow instructions with human feedback","author":"Ouyang","year":"2022"},{"key":"ref22","article-title":"Chain of thought prompting elicits reasoning in large language models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wei"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-021-03544-w"},{"key":"ref24","first-page":"1272","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kipf"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1189"},{"key":"ref26","article-title":"PaLM: Scaling language modeling with pathways","author":"Chowdhery","year":"2022"},{"key":"ref27","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref28","article-title":"AudioGPT: Understanding and generating speech, music, sound, and talking head","author":"Huang","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2020.01.021"},{"key":"ref31","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-short.107"},{"key":"ref33","article-title":"Unleashing the power of graph learning through LLM-based autonomous agents","author":"Wei","year":"2023"},{"key":"ref34","article-title":"Graph-ToolFormer: To empower LLMs with graph reasoning ability via prompt augmented by ChatGPT","author":"Zhang","year":"2023"},{"key":"ref35","article-title":"VisionLLM: Large language model is also an open-ended decoder for vision-centric tasks","author":"Wang","year":"2023"},{"key":"ref36","article-title":"PointLLM: Empowering large language models to understand point clouds","author":"Xu","year":"2023"},{"key":"ref37","first-page":"10211","article-title":"How powerful are graph neural networks?","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xu"},{"key":"ref38","first-page":"3608","article-title":"Graph attention networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Veli\u010dkovi\u0107"},{"key":"ref39","article-title":"A survey on multimodal large language models","author":"Yin","year":"2023"},{"key":"ref40","doi-asserted-by":"crossref","DOI":"10.1145\/3589334.3645682","article-title":"GraphTranslator: Aligning graph model to large language model for open-ended tasks","author":"Zhang","year":"2024"},{"key":"ref41","doi-asserted-by":"crossref","DOI":"10.1145\/3626772.3657775","article-title":"GraphGPT: Graph instruction tuning for large language models","author":"Tang","year":"2024"}],"container-title":["IEEE Transactions on Big Data"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6687317\/11433832\/11222956.pdf?arnumber=11222956","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,16]],"date-time":"2026-03-16T20:16:45Z","timestamp":1773692205000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11222956\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":41,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tbdata.2025.3627488","relation":{},"ISSN":["2332-7790","2372-2096"],"issn-type":[{"value":"2332-7790","type":"electronic"},{"value":"2372-2096","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}