{"id":22416485,"url":"https://github.com/yhLeeee/Awesome-LLMs-in-Graph-tasks","last_synced_at":"2025-08-01T01:31:17.335Z","repository":{"id":208546856,"uuid":"720092821","full_name":"yhLeeee/Awesome-LLMs-in-Graph-tasks","owner":"yhLeeee","description":"A curated collection of research papers exploring the utilization of LLMs for graph-related tasks.","archived":false,"fork":false,"pushed_at":"2024-11-05T04:01:02.000Z","size":16186,"stargazers_count":526,"open_issues_count":0,"forks_count":47,"subscribers_count":7,"default_branch":"main","last_synced_at":"2024-11-05T04:26:36.314Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":null,"has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/yhLeeee.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2023-11-17T15:06:21.000Z","updated_at":"2024-11-05T04:01:05.000Z","dependencies_parsed_at":"2023-12-13T04:02:04.160Z","dependency_job_id":"b19daa9d-7655-4a0e-a24e-f73886eed1e6","html_url":"https://github.com/yhLeeee/Awesome-LLMs-in-Graph-tasks","commit_stats":null,"previous_names":["yhleeee/awesome-llms-in-graph-tasks"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yhLeeee%2FAwesome-LLMs-in-Graph-tasks","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yhLeeee%2FAwesome-LLMs-in-Graph-tasks/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yhLeeee%2FAwesome-LLMs-in-Graph-tasks/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yhLeeee%2FAwesome-LLMs-in-Graph-tasks/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/yhLeeee","download_url":"https://codeload.github.com/yhLeeee/Awesome-LLMs-in-Graph-tasks/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":228321215,"owners_count":17901604,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-12-05T15:16:24.354Z","updated_at":"2025-08-01T01:31:17.319Z","avatar_url":"https://github.com/yhLeeee.png","language":null,"funding_links":[],"categories":["Graph Learning","Knowledge Integration","Other Lists","Topics","Others"],"sub_categories":["In-context Learning","TeX Lists","LLM \u0026 Knowledge Graph"],"readme":"\u003ch1 align=\"center\"\u003e Awesome-LLMs-in-Graph-tasks \u003c/a\u003e\u003c/h2\u003e\n\u003ch5 align=\"center\"\u003e If you like our project, please give us a star ⭐ on GitHub for the latest update.\u003c/h5\u003e\n\n\u003ch5 align=\"center\"\u003e\n\n![Awesome](https://cdn.rawgit.com/sindresorhus/awesome/d7305f38d29fed78fa85652e3a63e154dd8e8829/media/badge.svg) ![GitHub stars](https://img.shields.io/github/stars/yhLeeee/Awesome-LLMs-in-Graph-tasks.svg)\n\n\u003c/h5\u003e\n\n\u003e This is a collection of papers on leveraging **Large Language Models** in **Graph Tasks**. \nIt's based on our survey paper: [A Survey of Graph Meets Large Language Model: Progress and Future Directions](https://arxiv.org/abs/2311.12399). \n\n\u003e We will try to make this list updated frequently. If you found any error or any missed paper, please don't hesitate to open issues or pull requests.\n\n\u003e Our survey has been accepted by IJCAI 2024 survey track.\n\n## How can LLMs help improve graph-related tasks?\n\nWith the help of LLMs, there has been a notable shift in the way we interact with graphs, particularly those containing nodes associated with text attributes. The integration of LLMs with traditional GNNs can be mutually beneficial and enhance graph learning. While GNNs are proficient at capturing structural information, they primarily rely on semantically constrained embeddings as node features, limiting their ability to express the full complexities of the nodes. Incorporating LLMs, GNNs can be enhanced with stronger node features that effectively capture both structural and contextual aspects. On the other hand, LLMs excel at encoding text but often struggle to capture structural information present in graph data. Combining GNNs with LLMs can leverage the robust textual understanding of LLMs while harnessing GNNs' ability to capture structural relationships, leading to more comprehensive and powerful graph learning.\n\n\u003cp align=\"center\"\u003e\u003cimg src=\"Figures/overview.png\" width=75% height=75%\u003e\u003c/p\u003e\n\u003cp align=\"center\"\u003e\u003cem\u003eFigure 1.\u003c/em\u003e The overview of Graph Meets LLMs.\u003c/p\u003e\n\n\n## Summarizations based on proposed taxonomy\n\n\u003cp align=\"center\"\u003e\u003cimg src=\"Figures/summarization.png\" width=100% height=75%\u003e\u003c/p\u003e\n\n\u003cp align=\"left\"\u003e\u003cem\u003eTable 1.\u003c/em\u003e A summary of models that leverage LLMs to assist graph-related tasks in literature, ordered by their release time. \u003cb\u003eFine-tuning\u003c/b\u003e denotes whether it is necessary to fine-tune the parameters of LLMs, and \u0026hearts; indicates that models employ parameter-efficient fine-tuning (PEFT) strategies, such as LoRA and prefix tuning. \u003cb\u003ePrompting\u003c/b\u003e indicates the use of text-formatted prompts in LLMs, done manually or automatically. Acronyms in \u003cb\u003eTask\u003c/b\u003e: Node refers to node-level tasks; Link refers to link-level tasks; Graph refers to graph-level tasks; Reasoning refers to Graph Reasoning; Retrieval refers to Graph-Text Retrieval; Captioning refers to Graph Captioning.\u003c/p \u003e\n\n## Table of Contents\n\n- [Awesome-LLMs-in-Graph-tasks](#awesome-llms-in-graph-tasks)\n  - [How can LLMs help improve graph-related tasks](#how-can-llms-help-improve-graph-related-tasks)\n  - [Summarizations based on proposed taxonomy](#summarizations-based-on-proposed-taxonomy)\n  - [Table of Contents](#table-of-contents)\n  - [LLM as Enhancer](#llm-as-enhancer)\n  - [LLM as Predictor](#llm-as-predictor)\n  - [GNN-LLM Alignment](#gnn-llm-alignment)\n  - [Others](#others)\n  - [Contributing](#contributing)\n  - [Cite Us](#cite-us)\n\n\n## LLM as Enhancer\n* (_2022.03_) [ICLR' 2022] **Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction** [[Paper](https://arxiv.org/abs/2111.00064) | [Code](https://github.com/amzn/pecos/tree/mainline/examples/giant-xrt)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eGIANT\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/GIANT.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of GIANT.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.02_) [ICLR' 2023] **Edgeformers: Graph-Empowered Transformers for Representation Learning on Textual-Edge Networks** [[Paper](https://arxiv.org/abs/2302.11050) | [Code](https://github.com/PeterGriffinJin/Edgeformers)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eEdgeformers\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/Edgeformers.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of Edgeformers.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.05_) [KDD' 2023] **Graph-Aware Language Model Pre-Training on a Large Graph Corpus Can Help Multiple Graph Applications** [[Paper](https://arxiv.org/abs/2306.02592)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eGALM\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/GALM.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of GALM.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.06_) [KDD' 2023] **Heterformer: Transformer-based Deep Node Representation Learning on Heterogeneous Text-Rich Networks** [[Paper](https://dl.acm.org/doi/abs/10.1145/3580305.3599376?casa_token=M9bG1HLyTEYAAAAA:gIiYO9atgtxNaBgfKpy4D3N66QDkCFLFvlEADvzC8Pobe_EWausOknGnRFzdDF-Xnq-vbWAWMT1qkA) | [Code](https://github.com/PeterGriffinJin/Heterformer)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eHeterformer\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/Heterformers.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of Heterformer.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.05_) [ICLR' 2024] **Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learning** [[Paper](https://arxiv.org/abs/2305.19523) | [Code](https://github.com/XiaoxinHe/TAPE)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eTAPE\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/TAPE.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of TAPE.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.08_) [Arxiv' 2023] **Exploring the potential of large language models (llms) in learning on graphs** [[Paper](https://arxiv.org/abs/2307.03393)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eKEA\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/KEA.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of KEA.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.07_) [Arxiv' 2023] **Can Large Language Models Empower Molecular Property Prediction?** [[Paper](https://arxiv.org/abs/2307.07443) | [Code](https://github.com/ChnQ/LLM4Mol)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eLLM4Mol\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/LLM4Mol.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of LLM4Mol.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.08_) [Arxiv' 2023] **Simteg: A frustratingly simple approach improves textual graph learning** [[Paper](https://arxiv.org/abs/2308.02565) | [Code](https://github.com/vermouthdky/SimTeG)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eSimTeG\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/SimTeG.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of SimTeG.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.09_) [Arxiv' 2023] **Prompt-based Node Feature Extractor for Few-shot Learning on Text-Attributed Graphs** [[Paper](https://arxiv.org/abs/2309.02848)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eG-Prompt\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/G-Prompt.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of G-Prompt.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.09_) [Arxiv' 2023] **TouchUp-G: Improving Feature Representation through Graph-Centric Finetuning** [[Paper](https://arxiv.org/abs/2309.13885)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eTouchUp-G\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/TouchUp-G.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of TouchUp-G.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.09_) [ICLR' 2024] **One for All: Towards Training One Graph Model for All Classification Tasks** [[Paper](https://arxiv.org/abs/2310.00149) | [Code](https://github.com/LechengKong/OneForAll)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eOFA\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/OFA.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of OFA.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.10_) [Arxiv' 2023] **Learning Multiplex Embeddings on Text-rich Networks with One Text Encoder** [[Paper](https://arxiv.org/abs/2310.06684) | [Code](https://github.com/PeterGriffinJin/METERN-submit)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eMETERN\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/METERN.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of METERN.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.11_) [WSDM' 2024] **LLMRec: Large Language Models with Graph Augmentation for Recommendation** [[Paper](https://arxiv.org/abs/2311.00423) | [Code](https://github.com/HKUDS/LLMRec)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eLLMRec\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/LLMRec.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of LLMRec.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.11_) [NeurIPS' 2023] **WalkLM: A Uniform Language Model Fine-tuning Framework for Attributed Graph Embedding** [[Paper](https://openreview.net/forum?id=ZrG8kTbt70) | [Code](https://github.com/Melinda315/WalkLM)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eWalkLM\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/WalkLM.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of WalkLM.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2024.01_) [IJCAI' 2024] **Efficient Tuning and Inference for Large Language Models on Textual Graphs** [[Paper](https://arxiv.org/abs/2401.15569)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eENGINE\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/ENGINE.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of ENGINE.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2024.02_) [KDD' 2024] **ZeroG: Investigating Cross-dataset Zero-shot Transferability in Graphs** [[Paper](https://arxiv.org/abs/2402.11235)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eZeroG\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/ZeroG.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of ZeroG.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2024.02_) [Arxiv' 2024] **UniGraph: Learning a Cross-Domain Graph Foundation Model From Natural Language** [[Paper](https://arxiv.org/abs/2402.13630)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eUniGraph\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/UniGraph.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of UniGraph.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n\n* (_2024.02_) [CIKM' 2024] **Distilling Large Language Models for Text-Attributed Graph Learning** [[Paper](https://arxiv.org/abs/2402.12022)]\n   \u003cdetails close\u003e\n   \u003csummary\u003ePan, et al.\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/Pan_etal.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of Pan, et al.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n   \n* (_2024.10_) [CIKM' 2024] **When LLM Meets Hypergraph: A Sociological Analysis on Personality via Online Social Networks** [[Paper](https://arxiv.org/abs/2407.03568) | [Code](https://github.com/ZhiyaoShu/LLM-HGNN-MBTI)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eShu, et al.\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/shu2024llm.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of Shu, et al.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n   \n\n## LLM as Predictor\n\n* (_2023.05_) [NeurIPS' 2023] **Can language models solve graph problems in natural language?** [[Paper](https://arxiv.org/abs/2305.10037) | [Code](https://github.com/Arthur-Heng/NLGraph)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eNLGraph\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/NLGraph.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of NLGraph.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.05_) [Arxiv' 2023] **GPT4Graph: Can Large Language Models Understand Graph Structured Data? An Empirical Evaluation and Benchmarking** [[Paper](https://arxiv.org/abs/2305.15066) | [Code](https://anonymous.4open.science/r/GPT4Graph)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eGPT4Graph\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/GPT4Graph.png\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of GPT4Graph.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.06_) [NeurIPS' 2023] **GIMLET: A Unified Graph-Text Model for Instruction-Based Molecule Zero-Shot Learning** [[Paper](https://arxiv.org/abs/2306.13089) | [Code](https://github.com/zhao-ht/GIMLET)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eGIMLET\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/GIMLET.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of GIMLET.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.07_) [Arxiv' 2023] **Exploring the Potential of Large Language Models (LLMs) in Learning on Graphs** [[Paper](https://arxiv.org/abs/2307.03393) | [Code](https://github.com/CurryTang/Graph-LLM)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eFramework\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/Chen et al.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe designed prompts of Chen et al.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.08_) [Arxiv' 2023] **GIT-Mol: A Multi-modal Large Language Model for Molecular Science with Graph, Image, and Text** [[Paper](https://arxiv.org/abs/2308.06911)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eGIT-Mol\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/GIT-Mol.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of GIT-Mol.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.08_) [Arxiv' 2023] **Natural Language is All a Graph Needs** [[Paper](http://arxiv.org/abs/2308.07134) | [Code](https://github.com/agiresearch/InstructGLM)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eInstructGLM\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/InstructGLM.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of InstructGLM.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.08_) [Arxiv' 2023] **Evaluating Large Language Models on Graphs: Performance Insights and Comparative Analysis** [[Paper](https://arxiv.org/abs/2308.11224) | [Code](https://github.com/Ayame1006/LLMtoGraph)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eFramework\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/Liu et al.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe designed prompts of Liu et al.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.09_) [Arxiv' 2023] **Can LLMs Effectively Leverage Graph Structural Information: When and Why** [[Paper](https://arxiv.org/abs/2309.16595) | [Code](https://github.com/TRAIS-Lab/LLM-Structured-Data)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eFramework\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/Huang et al.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe designed prompts of Huang et al.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.10_) [Arxiv' 2023] **GraphText: Graph Reasoning in Text Space** [[Paper](https://arxiv.org/abs/2310.01089)] | [Code](https://github.com/AndyJZhao/GraphText)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eGraphText\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/GraphText.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of GraphText.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.10_) [Arxiv' 2023] **Talk like a Graph: Encoding Graphs for Large Language Models** [[Paper](https://arxiv.org/abs/2310.04560)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eFramework\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/Fatemi et al.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe designed prompts of Fatemi et al.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.10_) [Arxiv' 2023] **GraphLLM: Boosting Graph Reasoning Ability of Large Language Model** [[Paper](https://arxiv.org/abs/2310.05845) | [Code](https://github.com/mistyreed63849/Graph-LLM)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eGraphLLM\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/GraphLLM.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of GraphLLM.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.10_) [Arxiv' 2023] **Beyond Text: A Deep Dive into Large Language Model** [[Paper](https://arxiv.org/abs/2310.04944)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eFramework\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/Hu et al.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe designed prompts of Hu et al.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.10_) [EMNLP' 2023] **MolCA: Molecular Graph-Language Modeling with Cross-Modal Projector and Uni-Modal Adapter** [[Paper](https://arxiv.org/abs/2310.12798) | [Code](https://github.com/acharkq/MolCA)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eMolCA\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/MolCA.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of MolCA.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.10_) [Arxiv' 2023] **GraphGPT: Graph Instruction Tuning for Large Language Models** [[Paper](https://arxiv.org/abs/2310.13023v1) | [Code](https://github.com/HKUDS/GraphGPT)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eGraphGPT\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/GraphGPT.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of GraphGPT.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.10_) [EMNLP' 2023] **ReLM: Leveraging Language Models for Enhanced Chemical Reaction Prediction** [[Paper](https://arxiv.org/pdf/2310.13590.pdf) | [Code](https://github.com/syr-cn/ReLM)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eReLM\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/ReLM.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of ReLM.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.10_) [Arxiv' 2023] **LLM4DyG: Can Large Language Models Solve Problems on Dynamic Graphs?** [[Paper](https://arxiv.org/pdf/2310.17110.pdf)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eLLM4DyG\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/LLM4DyG.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of LLM4DyG.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.10_) [Arxiv' 2023] **Disentangled Representation Learning with Large Language Models for Text-Attributed Graphs** [[Paper](https://arxiv.org/abs/2310.18152)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eDGTL\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/DGTL.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of DGTL.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.11_) [Arxiv' 2023] **Which Modality should I use -- Text, Motif, or Image? : Understanding Graphs with Large Language Models** [[Paper](https://arxiv.org/abs/2311.09862)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eFramework\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/Das et al.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of Das et al.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.11_) [Arxiv' 2023] **InstructMol: Multi-Modal Integration for Building a Versatile and Reliable Molecular Assistant in Drug Discovery** [[Paper](https://arxiv.org/abs/2311.16208)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eInstructMol\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/InstructMol.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of InstructMol.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.12_) [Arxiv' 2023] **When Graph Data Meets Multimodal: A New Paradigm for Graph Understanding and Reasoning** [[Paper](https://arxiv.org/pdf/2312.10372.pdf)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eFramework\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/Ai et al.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of Ai et al.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2024.02_) [Arxiv' 2024] **Let Your Graph Do the Talking: Encoding Structured Data for LLMs** [[Paper](https://arxiv.org/abs/2402.05862)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eGraphToken\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/GraphToken.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of GraphToken.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2024.02_) [Arxiv' 2024] **Rendering Graphs for Graph Reasoning in Multimodal Large Language Models** [[Paper](https://arxiv.org/abs/2402.02130)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eGITA\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/GITA.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of GITA.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2024.02_) [WWW' 2024] **GraphTranslator: Aligning Graph Model to Large Language Model for Open-ended Tasks** [[Paper](https://arxiv.org/abs/2402.07197) | [Code](https://github.com/alibaba/GraphTranslator)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eGraphTranslator\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/GraphTranslator.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of GraphTranslator.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2024.02_) [Arxiv' 2024] **InstructGraph: Boosting Large Language Models via Graph-centric Instruction Tuning and Preference Alignment** [[Paper](https://arxiv.org/abs/2402.08785) | [Code](https://github.com/wjn1996/InstructGraph)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eInstructGraph\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/InstructGraph.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of InstructGraph.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2024.02_) [Arxiv' 2024] **LLaGA: Large Language and Graph Assistant** [[Paper](https://arxiv.org/abs/2402.08170) | [Code](https://github.com/VITA-Group/LLaGA)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eLLaGA\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/LLaGA.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of LLaGA.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2024.02_) [WWW' 2024] **Can GNN be Good Adapter for LLMs?** [[Paper](https://arxiv.org/abs/2402.12984)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eGraphAdapter\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/graphadapter.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of GraphAdapter.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2024.02_) [Arxiv' 2024] **HiGPT: Heterogeneous Graph Language Model** [[Paper](https://arxiv.org/abs/2402.16024) | [Code](https://github.com/HKUDS/HiGPT)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eHiGPT\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/HiGPT.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of HiGPT.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2024.02_) [Arxiv' 2024] **GraphWiz: An Instruction-Following Language Model for Graph Problems** [[Paper](https://arxiv.org/abs/2402.16029) | [Code](https://github.com/HKUDS/OpenGraph)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eGraphWiz\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/GraphWiz.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of GraphWiz.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2024.03_) [Arxiv' 2024] **OpenGraph: Towards Open Graph Foundation Models** [[Paper](https://arxiv.org/abs/2403.01121) | [Code](https://github.com/nuochenpku/Graph-Reasoning-LLM)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eOpenGraph\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/OpenGraph.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of OpenGraph.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n\n* (_2024.07_) [Arxiv' 2024] **GOFA: A Generative One-For-All Model for Joint Graph Language Modeling** [[Paper](https://arxiv.org/abs/2407.09709) | [Code](https://github.com/JiaruiFeng/GOFA)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eGOFA\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/GOFA.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of GOFA.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n   \n* (_2024.10_) [Arxiv' 2024] **Can Graph Descriptive Order Affect Solving Graph Problems with LLMs?** [[Paper](https://arxiv.org/abs/2402.07140)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eGraphDO\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/GraphDO.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of GraphDO.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n   \n## GNN-LLM Alignment\n* (_2020.08_) [Arxiv' 2020] **Graph-based Modeling of Online Communities for Fake News Detection** [[Paper](https://arxiv.org/abs/2008.06274) | [Code](https://github.com/shaanchandra/SAFER)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eSAFER\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/SAFER.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of SAFER.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2021.05_) [NeurIPS' 2021] **GraphFormers: GNN-nested Transformers for Representation Learning on Textual Graph** [[Paper](https://arxiv.org/abs/2105.02605) | [Code](https://github.com/microsoft/GraphFormers)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eGraphFormers\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/GraphFormers.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of GraphFormers.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2021.11_) [EMNLP' 2021] **Text2Mol: Cross-Modal Molecule Retrieval with Natural Language Queries** \n  [[Paper](https://aclanthology.org/2021.emnlp-main.47/) | [Code](https://github.com/cnedwards/text2mol)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eText2Mol\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/Text2Mol.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of Text2Mol.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2022.07_) [ACL' 2023] **Hidden Schema Networks**\n  [[Paper](https://arxiv.org/abs/2207.03777) | [Code](https://github.com/ramsesjsf/HiddenSchemaNetworks)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eHSN\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/HSN.png\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of HSN.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2022.09_) [Arxiv' 2022] **A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language** \n  [[Paper](https://arxiv.org/abs/2209.05481) | [Code](https://github.com/BingSu12/MoMu)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eMoMu\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/MoMu.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of MoMu.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2022.10_) [ICLR' 2023] **Learning on Large-scale Text-attributed Graphs via Variational Inference** \n  [[Paper](https://arxiv.org/abs/2210.14709) | [Code](https://github.com/AndyJZhao/GLEM)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eGLEM\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/GLEM.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of GLEM.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2022.12_) [NMI' 2023] **Multi-modal Molecule Structure-text Model for Text-based Editing and Retrieval** \n  [[Paper](https://arxiv.org/abs/2212.10789) | [Code](https://github.com/chao1224/MoleculeSTM)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eMoleculeSTM\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/MoleculeSTM.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of MoleculeSTM.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.04_) [Arxiv' 2023] **Train Your Own GNN Teacher: Graph-Aware Distillation on Textual Graphs** \n  [[Paper](https://arxiv.org/abs/2304.10668) | [Code](https://github.com/cmavro/GRAD)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eGRAD\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/GRAD.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of GRAD.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.05_) [ACL' 2023] **PATTON : Language Model Pretraining on Text-Rich Networks** \n  [[Paper](https://arxiv.org/abs/2305.12268) | [Code](https://github.com/PeterGriffinJin/Patton)]\n   \u003cdetails close\u003e\n   \u003csummary\u003ePatton\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/Patton.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of Patton.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.05_) [Arxiv' 2023] **ConGraT: Self-Supervised Contrastive Pretraining for Joint Graph and Text Embeddings** \n  [[Paper](https://arxiv.org/abs/2305.14321) | [Code](https://github.com/wwbrannon/congrat)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eConGraT\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/ConGraT.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of ConGraT.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.07_) [Arxiv' 2023] **Prompt Tuning on Graph-augmented Low-resource Text Classification** \n  [[Paper](https://arxiv.org/abs/2307.10230) | [Code](https://github.com/WenZhihao666/G2P2-conditional)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eG2P2\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/G2P2.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of G2P2.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.10_) [EMNLP' 2023] **GRENADE: Graph-Centric Language Model for Self-Supervised Representation Learning on Text-Attributed Graphs** \n  [[Paper](https://arxiv.org/abs/2310.15109) | [Code](https://github.com/bigheiniu/GRENADE)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eGRENADE\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/GRENADE.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of GRENADE.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.10_) [WWW' 2024] **Representation Learning with Large Language Models for Recommendation** \n  [[Paper](https://arxiv.org/abs/2310.15950) | [Code](https://github.com/HKUDS/RLMRec)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eRLMRec\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/RLMRec.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of RLMRec.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n* (_2023.10_) [EMNLP' 2023] **Pretraining Language Models with Text-Attributed Heterogeneous Graphs** \n  [[Paper](https://arxiv.org/abs/2310.12580) | [Code](https://github.com/Hope-Rita/THLM)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eTHLM\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/THLM.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of THLM.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n\n## Benchmarks\n* (_2025.1_) [COLING 2025]  **GraCoRe: Benchmarking Graph Comprehension and Complex Reasoning in Large Language Models** [[Paper](https://aclanthology.org/2025.coling-main.531/) | [Code](https://github.com/ZIKEYUAN/GraCoRe)]\n\n* (_2024.07_) [NeurIPS' 2024] **GLBench: A Comprehensive Benchmark for Graph with Large Language Models** [[Paper](https://arxiv.org/abs/2407.07457) | [Code](https://github.com/NineAbyss/GLBench)]\n  \n* (_2024.05_) [NeurIPS' 2024] **TEG-DB: A Comprehensive Dataset and Benchmark of Textual-Edge Graphs** [[Paper](https://arxiv.org/abs/2406.10310)][[Code](https://github.com/Zhuofeng-Li/TEG-Benchmark/tree/main)]\n\n\n\n## Others\n\n### LLM as Annotator\n\n* (_2023.10_) [ICLR' 2024] **Label-free Node Classification on Graphs with Large Language Models (LLMs)** [[Paper](https://arxiv.org/abs/2310.18152) | [Code](https://github.com/CurryTang/LLMGNN)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eLLM-GNN\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/LLM-GNN.png\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of LLM-GNN.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n\n* (_2024.09_) [NeurIPS' 2024] **Entity Alignment with Noisy Annotations from Large Language Models** [[Paper](https://arxiv.org/pdf/2405.16806) | [Code](https://github.com/chensyCN/llm4ea_official)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eLLM4EA\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/LLM4EA.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of LLM4EA.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n\n### LLM as Controller\n\n* (_2023.10_) [Arxiv' 2023] **Graph Neural Architecture Search with GPT-4** [[Paper](https://arxiv.org/abs/2310.01436)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eGPT4GNAS\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/GPT4GNAS.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of GPT4GNAS.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n\n### LLM as Sample Generator\n\n* (_2023.10_) [Arxiv' 2023] **Empower Text-Attributed Graphs Learning with Large Language Models (LLMs)** [[Paper](https://arxiv.org/abs/2310.09872)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eENG\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/ENG.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of ENG.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n\n### LLM as Similarity Analyzer\n\n* (_2023.11_) [Arxiv' 2023] **Large Language Models as Topological Structure Enhancers for Text-Attributed Graphs** [[Paper](https://arxiv.org/abs/2311.14324)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eFramework\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/Sun et al.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of Sun et al.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n\n### LLM for Robustness \n\n- (_2024.05_) [Arxiv' 2024] **Intruding with Words: Towards Understanding Graph Injection Attacks at the Text Level** [[Paper](https://arxiv.org/abs/2405.16405)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eLei, et al.\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/Lei, et al.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of Lei, et al..\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n\n- (_2024.08_) [Arxiv' 2024] **Can Large Language Models Improve the Adversarial Robustness of Graph Neural Networks?** [[Paper](https://arxiv.org/abs/2408.08685)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eLLM4RGNN\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/LLM4RGNN.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of LLM4RGNN.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n\n### LLM for Task Planning \n\n- (_2024.05_) [NeurIPS' 2024] **Can Graph Learning Improve Planning in LLM-based Agents?** [[Paper](https://arxiv.org/abs/2405.19119) | [Code](https://github.com/WxxShirley/GNN4TaskPlan)]\n  \u003cdetails close\u003e\n  \u003csummary\u003eGNN4TaskPlan\u003c/summary\u003e\n  \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/GNN4TaskPlan.jpg\" /\u003e\u003c/p\u003e\n  \u003cp align=\"center\"\u003e\u003cem\u003eThe definition of task planning and the proposed framework.\u003c/em\u003e\u003c/p\u003e\n  \u003c/details\u003e\n\n\n## Other Repos\n\nWe note that several repos also summarize papers on the integration of LLMs and graphs. However, we differentiate ourselves by organizing these papers leveraging a new and more granular taxonomy. We recommend researchers to explore some repositories for a comprehensive survey.\n\n- [Awesome-Graph-LLM](https://github.com/XiaoxinHe/Awesome-Graph-LLM), created by [Xiaoxin He](https://xiaoxinhe.github.io/) from NUS.\n\n- [Awesome-Large-Graph-Model](https://github.com/THUMNLab/awesome-large-graph-model), created by [Ziwei Zhang](https://zw-zhang.github.io/) from THU.\n\n- [Awesome-Language-Model-on-Graphs](https://github.com/PeterGriffinJin/Awesome-Language-Model-on-Graphs), created by [Bowen Jin](https://peterjin.me/) from UIUC.\n\nWe highly recommend a repository that summarizes the work on **Graph Prompt**, which is very close to Graph-LLM.\n\n- [Awesome-Graph-Prompt](https://github.com/WxxShirley/Awesome-Graph-Prompt), created by [Xixi Wu](https://wxxshirley.github.io/) from CUHK.\n\n\n## Contributing\n\nIf you have come across relevant resources, feel free to open an issue or submit a pull request.\n\n```\n* (_time_) [conference] **paper_name** [[Paper](link) | [Code](link)]\n   \u003cdetails close\u003e\n   \u003csummary\u003eModel name\u003c/summary\u003e\n   \u003cp align=\"center\"\u003e\u003cimg width=\"75%\" src=\"Figures/xxx.jpg\" /\u003e\u003c/p\u003e\n   \u003cp align=\"center\"\u003e\u003cem\u003eThe framework of model name.\u003c/em\u003e\u003c/p\u003e\n   \u003c/details\u003e\n```\n\n## Cite Us\n\nFeel free to cite this work if you find it useful to you!\n```\n@article{li2023survey,\n  title={A Survey of Graph Meets Large Language Model: Progress and Future Directions},\n  author={Li, Yuhan and Li, Zhixun and Wang, Peisong and Li, Jia and Sun, Xiangguo and Cheng, Hong and Yu, Jeffrey Xu},\n  journal={arXiv preprint arXiv:2311.12399},\n  year={2023}\n}\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FyhLeeee%2FAwesome-LLMs-in-Graph-tasks","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FyhLeeee%2FAwesome-LLMs-in-Graph-tasks","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FyhLeeee%2FAwesome-LLMs-in-Graph-tasks/lists"}