GraphLLM: Boosting Graph Reasoning Ability of Large Language Model

2023/10/09 by Ziwei Chai, Tianjie Zhang, Chai, Ziwei +11 · 14 citations
Computer Science · #Advanced Graph Neural Networks #Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences #Natural Language Processing Techniques #Topic Modeling

paper · pdf · doi:10.48550/arxiv.2310.05845

openalex publication_date 2023/10/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

The advancement of Large Language Models (LLMs) has remarkably pushed the boundaries towards artificial general intelligence (AGI), with their exceptional ability on understanding diverse types of information, including but not limited to images and audio. Despite this progress, a critical gap remains in empowering LLMs to proficiently understand and reason on graph data. Recent studies underscore LLMs' underwhelming performance on fundamental graph reasoning tasks. In this paper, we endeavor to unearth the obstacles that impede LLMs in graph reasoning, pinpointing the common practice of converting graphs into natural language descriptions (Graph2Text) as a fundamental bottleneck. To overcome this impediment, we introduce GraphLLM, a pioneering end-to-end approach that synergistically integrates graph learning models with LLMs. This synergy equips LLMs with the ability to proficiently interpret and reason on graph data, harnessing the superior expressive power of graph learning models. Our empirical evaluations across four fundamental graph reasoning tasks validate the effectiveness of GraphLLM. The results exhibit a substantial average accuracy enhancement of 54.44%, alongside a noteworthy context reduction of 96.45% across various graph reasoning tasks.

Cited by

• GLOW: Graph-Language Co-Reasoning for Agentic Workflow Performance Prediction
• Can TabPFN Compete with GNNs for Node Classification via Graph Tabularization?
• DialogGraph-LLM: Graph-Informed LLMs for End-to-End Audio Dialogue Intent Recognition
• GraphChain: Large Language Models for Large-scale Graph Analysis via Tool Chaining
• Graph-S3: Enhancing Agentic textual Graph Retrieval with Synthetic Stepwise Supervision
• Rethinking and Benchmarking Large Language Models for Graph Reasoning
• Understanding and Enhancing the Planning Capability of Language Models via Multi-Token Prediction
• Benefits and Pitfalls of Reinforcement Learning for Language Model Planning: A Theoretical Perspective
• SSTAG: Structure-Aware Self-Supervised Learning Method for Text-Attributed Graphs
• AssemMate: Graph-Based LLM for Robotic Assembly Assistance
• Self-Exploring Language Models for Explainable Link Forecasting on Temporal Graphs via Reinforcement Learning
• SAGE-HLS: Syntax-Aware AST-Guided LLM for High-Level Synthesis Code Generation
• A Comprehensive Data-centric Overview of Federated Graph Learning
• SAFT: Structure-Aware Fine-Tuning of LLMs for AMR-to-Text Generation

Related

• Rethinking and Benchmarking Large Language Models for Graph Reasoning
• GraphInstruct: Empowering Large Language Models with Graph Understanding and Reasoning Capability
• GUNDAM: Aligning Large Language Models with Graph Understanding
• Talk like a Graph: Encoding Graphs for Large Language Models
• GraphOmni: A Comprehensive and Extendable Benchmark Framework for Large Language Models on Graph-theoretic Tasks