SILTD: Structural Information for LLM-Generated Text Detection

doi:10.1007/s13042-025-02616-x

	SILTD: Structural Information for LLM-Generated Text Detection
	Yang, Jing 1,2; Wang, Shi 1,2; Zi, Kangli 1,2; Sun, Yanshun 1,2; Huang, Yuwei 1,2; Luo, Tianyu 1,2
	2025-05-23
发表期刊	INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS
ISSN	1868-8071
页码	16
摘要	The rapid development of large language models (LLMs) has significantly improved the quality and diversity of AI-generated content(AIGC). LLM-Generated text detection plays an important role in preventing the harmful misuse of large language models. Existing approaches primarily analyze texts individually, overlooking the structural relationships between them. This limitation restricts their ability to generalize across diverse LLMs, as they fail to capture the shared statistical patterns inherent in generated texts. To address this, an unsupervised-based structural information for LLM-generated text detection (SILTD) method is proposed. The key insight is that texts from different LLMs exhibit latent similarities in their generative statistical space, which can be modeled to improve cross-model generalization. First, we construct a multi-relational text graph based on the similarity of text features, which aims to model the intricate similarities and correlations between texts. Second, we propose a novel unsupervised graph clustering method. The multi-relational graph is transformed into an encoding tree, which is then optimized based on a two-dimensional structure entropy minimization algorithm to achieve hierarchical clustering of texts. Structural entropy minimization enables achieving high-quality clusters, by measuring the uncertainty of random walks within the graph. Finally, we introduce a new method that measures text similarity and computes the intensity of text aggregation within each cluster, to perform in-cluster label inference. Extensive experiments show that, compared to baseline methods, our approach is more effective and generalizable in detecting six popular LLMs across five datasets.
关键词	LLM-generated text detection Structural information Multi-relational graph Clustering
DOI	10.1007/s13042-025-02616-x
收录类别	SCI
语种	英语
资助项目	National Key Research and Development Program of China[2022YFC3302300] ; Advanced Research Project[7090201050307] ; National 242 Information Security Program[2023A105]
WOS研究方向	Computer Science
WOS类目	Computer Science, Artificial Intelligence
WOS记录号	WOS:001493346900001
出版者	SPRINGER HEIDELBERG
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/42402
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Wang, Shi; Zi, Kangli
作者单位	1.Chinese Acad Sci, Inst Comp Technol, Key Lab Intelligent Informat Proc, Beijing 100190, Peoples R China 2.Univ Chinese Acad Sci, Beijing 100049, Peoples R China
推荐引用方式 GB/T 7714	Yang, Jing,Wang, Shi,Zi, Kangli,et al. SILTD: Structural Information for LLM-Generated Text Detection[J]. INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS,2025:16.
APA	Yang, Jing,Wang, Shi,Zi, Kangli,Sun, Yanshun,Huang, Yuwei,&Luo, Tianyu.(2025).SILTD: Structural Information for LLM-Generated Text Detection.INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS,16.
MLA	Yang, Jing,et al."SILTD: Structural Information for LLM-Generated Text Detection".INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS (2025):16.