arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2501.01203cs.SI
收藏

HetGCoT:异构图增强的链式思考LLM推理用于学术问答

HetGCoT: Heterogeneous Graph-Enhanced Chain-of-Thought LLM Reasoning for Academic Question Answering

University of Technology Sydney(悉尼科技大学);University of Texas at Austin(德克萨斯大学奥斯汀分校)

Runsong Jia, Mengjia Wu, Ying Ding, Jie Lu, Yi Zhang

AI总结:

HetGCoT通过异构图增强链式思考LLM推理,提升学术问答的可解释性和准确性。

摘要:

学术问答(QA)在异构学术网络中提出了独特的挑战,需要结构理解和可解释的推理。虽然图神经网络(GNN)能够捕捉结构化图信息,而大型语言模型(LLM)在语义理解方面表现出强大的能力,但当前方法在推理层面缺乏整合。我们提出了HetGCoT框架,使LLM能够有效利用和学习图信息以进行可解释的学术问答推理。我们的框架引入了三个技术贡献:(1)一个将异构图结构信息转化为LLM可处理推理链的框架;(2)一个自适应元路径选择机制,用于识别特定查询的相关子图;(3)一个多步骤推理策略,系统地将图上下文整合到推理过程中。在OpenAlex和DBLP数据集上的实验表明,我们的方法优于所有现有最佳基线。该框架在不同LLM架构上表现出适应性,并适用于各种学术问答任务。

英文摘要:

Academic question answering (QA) in heterogeneous scholarly networks presents unique challenges requiring both structural understanding and interpretable reasoning. While graph neural networks (GNNs) capture structured graph information and large language models (LLMs) demonstrate strong capabilities in semantic comprehension, current approaches lack integration at the reasoning level. We propose HetGCoT, a framework enabling LLMs to effectively leverage and learn information from graphs to reason interpretable academic QA results. Our framework introduces three technical contributions: (1) a framework that transforms heterogeneous graph structural information into LLM-processable reasoning chains, (2) an adaptive metapath selection mechanism identifying relevant subgraphs for specific queries, and (3) a multi-step reasoning strategy systematically incorporating graph contexts into the reasoning process. Experiments on OpenAlex and DBLP datasets show our approach outperforms all sota baselines. The framework demonstrates adaptability across different LLM architectures and applicability to various scholarly question answering tasks.

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。

↑