arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2409.20053cs.AIcs.CLcs.LG
收藏

GUNDAM:通过图理解对齐大语言模型

GUNDAM: Aligning Large Language Models with Graph Understanding

Renmin University of China(中国人民大学);University of Chinese Academy of Sciences(中国科学院大学)

Sheng Ouyang, Yulan Hu, Ge Chen, Yong Liu

AI总结:

针对现有LLMs图学习研究重文本特征、轻结构理解的不足,本研究提出GUNDAM模型以增强LLMs的图结构理解与推理能力,实验证明其性能优于SOTA基线,并通过理论分析揭示了推理路径的作用。

摘要:

大语言模型(LLMs)在文本数据处理方面已取得令人瞩目的成果,这引发了人们将这类模型应用于文本数据之外(例如图数据)的兴趣。在图学习领域,利用LLMs理解和处理图结构数据的研究正日益受到关注。现有研究主要聚焦于具有丰富文本特征的图(如知识图谱或文本属性图),这类研究利用了LLMs的文本处理能力,但对图结构的处理不够充分。本工作专门旨在评估并增强LLMs理解和利用图数据本身固有结构知识的能力,而非仅关注文本内容丰富的图。为实现这一目标,我们提出了**G**raph **U**nderstanding for **N**atural Language **D**riven **A**nalytical **M**odel(GUNDAM,自然语言驱动分析模型的图理解模块)。该模型对LLMs进行适配,使其能更好地理解和处理图数据的结构,从而能够利用图本身的结构执行复杂推理任务。我们在图推理基准上开展的实验评估不仅证实了GUNDAM的性能优于用于对比的SOTA(state-of-the-art,当前最优)基线,还揭示了影响LLMs图推理能力的关键因素。此外,我们提供了理论分析,阐明了推理路径如何能够增强LLMs的推理能力。

英文摘要:

Large Language Models (LLMs) have achieved impressive results in processing text data, which has sparked interest in applying these models beyond textual data, such as graphs. In the field of graph learning, there is a growing interest in harnessing LLMs to comprehend and manipulate graph-structured data. Existing research predominantly focuses on graphs with rich textual features, such as knowledge graphs or text attribute graphs, leveraging LLMs' ability to process text but inadequately addressing graph structure. This work specifically aims to assess and enhance LLMs' abilities to comprehend and utilize the structural knowledge inherent in graph data itself, rather than focusing solely on graphs rich in textual content. To achieve this, we introduce the \textbf{G}raph \textbf{U}nderstanding for \textbf{N}atural Language \textbf{D}riven \textbf{A}nalytical \textbf{M}odel (\model). This model adapts LLMs to better understand and engage with the structure of graph data, enabling them to perform complex reasoning tasks by leveraging the graph's structure itself. Our experimental evaluations on graph reasoning benchmarks not only substantiate that \model~ outperforms the SOTA baselines for comparisons. But also reveals key factors affecting the graph reasoning capabilities of LLMs. Moreover, we provide a theoretical analysis illustrating how reasoning paths can enhance LLMs' reasoning capabilities.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑