arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2603.12290cs.IRcs.AI
收藏

通过LLM增强的文本丰富图学习检测学术网络中的误引

Detecting Miscitation on the Scholarly Web through LLM-Augmented Text-Rich Graph Learning

Chinese Academy of Sciences & City University of Hong Kong(中国科学院与香港城市大学);City University of Hong Kong(香港城市大学);Shenzhen University & Beijing Dongbi Data Technology(深圳大学与北京东碧数据技术);University of Chinese Academy of Sciences(中国科学院大学)

Huidong Wu, Haojia Xiang, Jingtong Gao, Xiangyu Zhao, Dengsheng Wu, Jianping Li

AI总结:

本文提出LAGMiD框架,利用LLM进行深度语义推理,结合图神经网络实现高效误引检测,通过证据链推理和知识蒸馏降低计算成本,实验显示效果优于现有方法。

摘要:

学术网络是一个由引用连接的知识庞大网络。然而,该系统正受到误引的威胁,即引用不支持甚至反驳其被引用的主张。当前的误引检测方法主要依赖语义相似性或网络异常,难以捕捉引用上下文与整体网络位置之间的细微关系。虽然大语言模型(LLM)在语义推理方面具有强大能力,但其部署受幻觉风险和高计算成本限制。本文介绍LLM增强的图学习误引检测器(LAGMiD),一种新颖的框架,利用LLM对引用图进行深度语义推理,并将此知识蒸馏到图神经网络(GNN)中,以实现高效且可扩展的误引检测。具体而言,LAGMiD引入证据链推理机制,利用链式思维提示进行多跳引用追踪并评估语义保真度。为减少LLM推理成本,我们设计了一种知识蒸馏方法,使GNN嵌入与中间LLM推理状态对齐。协作学习策略进一步将复杂案例路由到LLM,同时优化GNN以实现基于结构的泛化。在三个真实世界基准测试中,LAGMiD实现了最先进的误引检测,同时显著降低了推理成本。

英文摘要:

Scholarly web is a vast network of knowledge connected by citations. However, this system is increasingly compromised by miscitation, where references do not support or even contradict the claims they are cited for. Current miscitation detection methods, which primarily rely on semantic similarity or network anomalies, struggle to capture the nuanced relationship between a citation's context and its place in the wider network. While large language models (LLMs) offer powerful capabilities in semantic reasoning for this task, their deployment is hindered by hallucination risks and high computational costs. In this work, we introduce LLM-Augmented Graph Learning-based Miscitation Detector (LAGMiD), a novel framework that leverages LLMs for deep semantic reasoning over citation graphs and distills this knowledge into graph neural networks (GNNs) for efficient and scalable miscitation detection. Specifically, LAGMiD introduces an evidence-chain reasoning mechanism, which uses chain-of-thought prompting, to perform multi-hop citation tracing and assess semantic fidelity. To reduce LLM inference costs, we design a knowledge distillation method aligning GNN embeddings with intermediate LLM reasoning states. A collaborative learning strategy further routes complex cases to the LLM while optimizing the GNN for structure-based generalization. Experiments on three real-world benchmarks show that LAGMiD achieves state-of-the-art miscitation detection with significantly reduced inference cost.

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。

↑