Awesome-Language-Model-on-Graphs

Awesome-Language-Model-on-Graphs

图上大语言模型研究进展及资源汇总

该资源列表汇总了图上大语言模型(LLMs on Graphs)领域的前沿研究成果。内容涵盖纯图、文本属性图和文本配对图等多个方面,包括数据集、直接回答、启发式推理和算法推理等关键主题。列表基于综述论文整理,并持续更新,为研究人员提供全面参考,推动图上大语言模型研究进展。

LLM推理基准测试知识图谱Github开源项目

Awesome-Language-Model-on-Graphs Awesome

A curated list of papers and resources about large language models (LLMs) on graphs based on our survey paper: Large Language Models on Graphs: A Comprehensive Survey.

This repo will be continuously updated. Don't forget to star <img src="./fig/star.svg" width="15" height="15" /> it and keep tuned!

Please cite the paper in Citations if you find the resource helpful for your research. Thanks!

<p align="center"> <img src="./fig/intro.svg" width="90%" style="align:center;"/> </p>

Why LLMs on graphs?

Large language models (LLMs), such as ChatGPT and LLaMA, are creating significant advancements in natural language processing, due to their strong text encoding/decoding ability and newly found emergent capability (e.g., reasoning). While LLMs are mainly designed to process pure texts, there are many real-world scenarios where text data are associated with rich structure information in the form of graphs (e.g., academic networks, and e-commerce networks) or scenarios where graph data are captioned with rich textual information (e.g., molecules with descriptions). Besides, although LLMs have shown their pure text-based reasoning ability, it is underexplored whether such ability can be generalized to graph scenarios (i.e., graph-based reasoning). In this paper, we provide a comprehensive review of scenarios and techniques related to large language models on graphs.

Contents

Keywords Convention

The Transformer architecture used in the work, e.g., EncoderOnly, DecoderOnly, EncoderDecoder.

The size of the large language model, e.g., medium (i.e., less than 1B parameters), LLM (i.e., more than 1B parameters).

Perspectives

  1. Unifying Large Language Models and Knowledge Graphs: A Roadmap. preprint

    Shirui Pan, Linhao Luo, Yufei Wang, Chen Chen, Jiapu Wang, Xindong Wu [PDF], 2023.6

  2. Integrating Graphs with Large Language Models: Methods and Prospects preprint

    Shirui Pan, Yizhen Zheng, Yixin Liu [PDF], 2023.10

  3. Towards graph foundation models: A survey and beyond. preprint

    Jiawei Liu, Cheng Yang, Zhiyuan Lu, Junze Chen, Yibo Li, Mengmei Zhang, Ting Bai, Yuan Fang, Lichao Sun, Philip S. Yu, Chuan Shi. [PDF], 2023.10

  4. A Survey of Graph Meets Large Language Model: Progress and Future Directions. preprint

    Yuhan Li, Zhixun Li, Peisong Wang, Jia Li, Xiangguo Sun, Hong Cheng, Jeffrey Xu Yu. [PDF], 2023.11

Pure Graphs

<img src="./fig/star.svg" width="15" height="15" /> Datasets

Table 3 in our survey paper Large Language Models on Graphs: A Comprehensive Survey.

<p align="center"> <img src="./fig/puregraph-data.jpg" width="90%" style="align:center;"/> </p>

<img src="./fig/star.svg" width="15" height="15" /> Direct Answering

  1. Can Language Models Solve Graph Problems in Natural Language? preprint

    Heng Wang, Shangbin Feng, Tianxing He, Zhaoxuan Tan, Xiaochuang Han, Yulia Tsvetkov. [PDF] [Code], 2023.5,

  2. GPT4Graph: Can Large Language Models Understand Graph Structured Data ? An Empirical Evaluation and Benchmarking. preprint

    Jiayan Guo, Lun Du, Hengyu Liu, Mengyu Zhou, Xinyi He, Shi Han. [PDF], 2023.5,

  3. Evaluating Large Language Models on Graphs: Performance Insights and Comparative Analysis. preprint

    Chang Liu, Bo Wu. [PDF] [Code], 2023.8, [PDF], 2023.5,

  4. Talk Like A Graph: Encoding Graphs For Large Language Models. preprint

    Bahare Fatemi, Jonathan Halcrow, Bryan Perozzi. [PDF], 2023.10,

  5. GraphLLM: Boosting Graph Reasoning Ability of Large Language Model. preprint

    Ziwei Chai, Tianjie Zhang, Liang Wu, Kaiqiao Han, Xiaohai Hu, Xuanwen Huang, Yang Yang. [PDF] [Code], 2023.10,

  6. LLM4DyG: Can Large Language Models Solve Problems on Dynamic Graphs?. preprint

    Zeyang Zhang, Xin Wang, Ziwei Zhang, Haoyang Li, Yijian Qin, Simin Wu, Wenwu Zhu [PDF] [Code], 2023.10,

  7. Which Modality should I use - Text, Motif, or Image? : Understanding Graphs with Large Language Models. preprint

    Debarati Das, Ishaan Gupta, Jaideep Srivastava, Dongyeop Kang [PDF] [Code], 2023.11,

  8. GraphArena: Benchmarking Large Language Models on Graph Computational Problems. preprint

    Jianheng Tang, Qifan Zhang, Yuhan Li, Jia Li [PDF] [Code], 2024.7,

<img src="./fig/star.svg" width="15" height="15" /> Heuristic Reasoning

  1. StructGPT: A General Framework for Large Language Model to Reason over Structured Data. preprint

    Jinhao Jiang, Kun Zhou, Zican Dong, Keming Ye, Wayne Xin Zhao, Ji-Rong Wen. [PDF] [Code], 2023.5,

  2. Think-on-Graph: Deep and Responsible Reasoning of Large Language Model on Knowledge Graph. preprint

    Jiashuo Sun, Chengjin Xu, Lumingyuan Tang, Saizhuo Wang, Chen Lin, Yeyun Gong, Lionel M. Ni, Heung-Yeung Shum, Jian Guo. [PDF] [Code], 2023.7,

  3. Exploring Large Language Model for Graph Data Understanding in Online Job Recommendations. preprint

    Likang Wu, Zhaopeng Qiu, Zhi Zheng, Hengshu Zhu, Enhong Chen. [PDF] [Code], 2023.7,

  4. Knowledge Graph Prompting for Multi-Document Question Answering. AAAI2024

    Yu Wang, Nedim Lipka, Ryan Rossi, Alex Siu, Ruiyi Zhang, Tyler Derr. [PDF] [Code], 2023.8,

  5. ChatRule: Mining Logical Rules with Large Language Models for Knowledge Graph Reasoning. preprint

    Linhao Luo, Jiaxin Ju, Bo Xiong, Yuan-Fang Li, Gholamreza Haffari, Shirui Pan. [PDF] [Code], 2023.9,

  6. Reasoning on Graphs: Faithful and Interpretable Large Language Model Reasoning. preprint

    Linhao Luo, Yuan-Fang Li, Gholamreza Haffari, Shirui Pan. [PDF] [Code], 2023.10,

  7. Thought Propagation: An Analogical Approach to Complex Reasoning with Large Language Models. preprint

    Junchi Yu, Ran He, Rex Ying. [PDF], 2023.10,

  8. Large Language Models Can Learn Temporal Reasoning. preprint

    Siheng Xiong, Ali Payani, Ramana Kompella, Faramarz Fekri. [PDF], 2024.1,

  9. Exploring the Limitations of Graph Reasoning in Large Language Models. preprint

    Palaash Agrawal, Shavak Vasania, Cheston Tan. [PDF], 2024.2,

  10. Rendering Graphs for Graph Reasoning in Multimodal Large Language Models. preprint

    Yanbin Wei, Shuai Fu, Weisen Jiang, James T. Kwok, Yu Zhang. [PDF], 2024.2,

  11. Graph-enhanced Large Language Models in Asynchronous Plan Reasoning. preprint

    Fangru Lin, Emanuele La Malfa, Valentin Hofmann, Elle Michelle Yang, Anthony Cohn, Janet B. Pierrehumbert. [PDF], 2024.2,

  12. Microstructures and Accuracy of Graph Recall by Large Language Models. preprint

    Yanbang Wang, Hejie Cui, Jon Kleinberg. [PDF], 2024.2,

  13. Structure Guided Prompt: Instructing Large Language Model in Multi-Step Reasoning by Exploring Graph Structure of the Text. preprint

    Kewei Cheng, Nesreen K. Ahmed, Theodore Willke, Yizhou Sun. [PDF], 2024.2,

  14. GraphInstruct: Empowering Large Language Models with Graph Understanding and Reasoning Capability. preprint

    Zihan Luo, Xiran Song, Hong Huang, Jianxun Lian, Chenhao Zhang, Jinqi Jiang, Xing Xie, Hai Jin. [PDF], 2024.3,

  15. Call Me When Necessary: LLMs can Efficiently and Faithfully Reason over Structured Environments. preprint

    Sitao Cheng, Ziyuan Zhuang, Yong Xu, Fangkai Yang, Chaoyun Zhang, Xiaoting Qin, Xiang Huang, Ling Chen, Qingwei Lin, Dongmei Zhang, Saravan Rajmohan, Qi Zhang. [PDF], 2024.3,

  16. **Exploring the

编辑推荐精选

openai-agents-python

openai-agents-python

OpenAI Agents SDK,助力开发者便捷使用 OpenAI 相关功能。

openai-agents-python 是 OpenAI 推出的一款强大 Python SDK,它为开发者提供了与 OpenAI 模型交互的高效工具,支持工具调用、结果处理、追踪等功能,涵盖多种应用场景,如研究助手、财务研究等,能显著提升开发效率,让开发者更轻松地利用 OpenAI 的技术优势。

Hunyuan3D-2

Hunyuan3D-2

高分辨率纹理 3D 资产生成

Hunyuan3D-2 是腾讯开发的用于 3D 资产生成的强大工具,支持从文本描述、单张图片或多视角图片生成 3D 模型,具备快速形状生成能力,可生成带纹理的高质量 3D 模型,适用于多个领域,为 3D 创作提供了高效解决方案。

3FS

3FS

一个具备存储、管理和客户端操作等多种功能的分布式文件系统相关项目。

3FS 是一个功能强大的分布式文件系统项目,涵盖了存储引擎、元数据管理、客户端工具等多个模块。它支持多种文件操作,如创建文件和目录、设置布局等,同时具备高效的事件循环、节点选择和协程池管理等特性。适用于需要大规模数据存储和管理的场景,能够提高系统的性能和可靠性,是分布式存储领域的优质解决方案。

TRELLIS

TRELLIS

用于可扩展和多功能 3D 生成的结构化 3D 潜在表示

TRELLIS 是一个专注于 3D 生成的项目,它利用结构化 3D 潜在表示技术,实现了可扩展且多功能的 3D 生成。项目提供了多种 3D 生成的方法和工具,包括文本到 3D、图像到 3D 等,并且支持多种输出格式,如 3D 高斯、辐射场和网格等。通过 TRELLIS,用户可以根据文本描述或图像输入快速生成高质量的 3D 资产,适用于游戏开发、动画制作、虚拟现实等多个领域。

ai-agents-for-beginners

ai-agents-for-beginners

10 节课教你开启构建 AI 代理所需的一切知识

AI Agents for Beginners 是一个专为初学者打造的课程项目,提供 10 节课程,涵盖构建 AI 代理的必备知识,支持多种语言,包含规划设计、工具使用、多代理等丰富内容,助您快速入门 AI 代理领域。

AEE

AEE

AI Excel全自动制表工具

AEE 在线 AI 全自动 Excel 编辑器,提供智能录入、自动公式、数据整理、图表生成等功能,高效处理 Excel 任务,提升办公效率。支持自动高亮数据、批量计算、不规则数据录入,适用于企业、教育、金融等多场景。

UI-TARS-desktop

UI-TARS-desktop

基于 UI-TARS 视觉语言模型的桌面应用,可通过自然语言控制计算机进行多模态操作。

UI-TARS-desktop 是一款功能强大的桌面应用,基于 UI-TARS(视觉语言模型)构建。它具备自然语言控制、截图与视觉识别、精确的鼠标键盘控制等功能,支持跨平台使用(Windows/MacOS),能提供实时反馈和状态显示,且数据完全本地处理,保障隐私安全。该应用集成了多种大语言模型和搜索方式,还可进行文件系统操作。适用于需要智能交互和自动化任务的场景,如信息检索、文件管理等。其提供了详细的文档,包括快速启动、部署、贡献指南和 SDK 使用说明等,方便开发者使用和扩展。

Wan2.1

Wan2.1

开源且先进的大规模视频生成模型项目

Wan2.1 是一个开源且先进的大规模视频生成模型项目,支持文本到图像、文本到视频、图像到视频等多种生成任务。它具备丰富的配置选项,可调整分辨率、扩散步数等参数,还能对提示词进行增强。使用了多种先进技术和工具,在视频和图像生成领域具有广泛应用前景,适合研究人员和开发者使用。

爱图表

爱图表

全流程 AI 驱动的数据可视化工具,助力用户轻松创作高颜值图表

爱图表(aitubiao.com)就是AI图表,是由镝数科技推出的一款创新型智能数据可视化平台,专注于为用户提供便捷的图表生成、数据分析和报告撰写服务。爱图表是中国首个在图表场景接入DeepSeek的产品。通过接入前沿的DeepSeek系列AI模型,爱图表结合强大的数据处理能力与智能化功能,致力于帮助职场人士高效处理和表达数据,提升工作效率和报告质量。

Qwen2.5-VL

Qwen2.5-VL

一款强大的视觉语言模型,支持图像和视频输入

Qwen2.5-VL 是一款强大的视觉语言模型,支持图像和视频输入,可用于多种场景,如商品特点总结、图像文字识别等。项目提供了 OpenAI API 服务、Web UI 示例等部署方式,还包含了视觉处理工具,有助于开发者快速集成和使用,提升工作效率。

下拉加载更多