GraphLLM: Boosting Graph Reasoning Ability of Large Language Model

TL;DR

GraphLLM introduces an end-to-end method combining graph learning models with LLMs to significantly improve graph reasoning capabilities, addressing a key bottleneck and achieving substantial accuracy and context reduction improvements.

Contribution

It presents a novel end-to-end approach that integrates graph learning models with LLMs, enhancing their ability to understand and reason on graph data.

Findings

Average accuracy improved by 54.44%.

Context reduction of 96.45% achieved.

Effective across four fundamental graph reasoning tasks.

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.