arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2402.10359cs.LGcs.CL
收藏

我们能否为图学习任务对大型语言模型进行软提示?

Can we Soft Prompt LLMs for Graph Learning Tasks?

University of Notre Dame(圣母大学);National University of Singapore(新加坡国立大学)

Zheyuan Liu, Xiaoxin He, Yijun Tian, Nitesh V. Chawla

AI总结:

本文提出GraphPrompter框架,通过软提示将图神经网络编码的图信息与大型语言模型对齐,在节点分类和链接预测任务上验证了LLMs作为图预测器的有效性。

摘要:

图在表示现实世界应用中的复杂关系(如社交网络、生物数据和引文网络)方面扮演着重要角色。近年来,大型语言模型(LLMs)在各个领域取得了巨大成功,这使得将LLMs应用于图变得尤为吸引人。然而,由于图模态与文本模态之间的差异和不匹配,直接将LLMs应用于图模态会带来独特的挑战。因此,为了进一步探究LLMs理解图信息的潜力,我们引入了GraphPrompter,一种通过软提示将图信息与LLMs对齐的新型框架。具体来说,GraphPrompter由两个主要组件组成:一个用于编码复杂图信息的图神经网络,以及一个有效处理文本信息的LLM。在节点分类和链接预测任务下,对各种基准数据集进行的全面实验证明了我们提出方法的有效性。GraphPrompter框架揭示了LLMs作为图相关任务预测器的强大能力,使研究人员能够更有效地在广泛的现实世界图场景中利用LLMs。

英文摘要:

Graph plays an important role in representing complex relationships in real-world applications such as social networks, biological data and citation networks. In recent years, Large Language Models (LLMs) have achieved tremendous success in various domains, which makes applying LLMs to graphs particularly appealing. However, directly applying LLMs to graph modalities presents unique challenges due to the discrepancy and mismatch between the graph and text modalities. Hence, to further investigate LLMs' potential for comprehending graph information, we introduce GraphPrompter, a novel framework designed to align graph information with LLMs via soft prompts. Specifically, GraphPrompter consists of two main components: a graph neural network to encode complex graph information and an LLM that effectively processes textual information. Comprehensive experiments on various benchmark datasets under node classification and link prediction tasks demonstrate the effectiveness of our proposed method. The GraphPrompter framework unveils the substantial capabilities of LLMs as predictors in graph-related tasks, enabling researchers to utilize LLMs across a spectrum of real-world graph scenarios more effectively.

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。

↑