GraphLLM: Boosting Graph Reasoning Ability of Large Language Model

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 integration equips LLMs with the capability to proficiently interpret and reason on graph data, harnessing the superior expressive power of graph learning models. The AI community has witnessed the emergence of powerful pre-trained Large Language Models (LLMs) (Brown et al., 2020; Chowdhery et al., 2022; OpenAI, 2023; Touvron et al., 2023), which leads to the pursuit of the potential realization of Artificial General Intelligence (AGI). Inspired by the fact that an intelligent agent, like the human brain, processes information of diverse types, there is a trend towards empowering LLMs to understand various forms of data, such as audio (Huang et al., 2023) and images (Alayrac et al., 2022). Despite significant strides in interpreting multimodal information (Yin et al., 2023), empowering LLMs to understand graph data remains relatively unexplored. Graphs, which represent entities as nodes and relationships as edges, are ubiquitous in numerous fields, e.g. An intelligent agent is expected to reason with graph data to facilitate many tasks such as drug discovery (Stokes et al., 2020) and chip design (Mirhoseini et al., 2021).