CACRE: A Weakly Supervised Method for Cross-Attention Contrastive Relation Extraction With Large Language Models

doi:10.1109/ACCESS.2026.3660343

CSpace

	CACRE: A Weakly Supervised Method for Cross-Attention Contrastive Relation Extraction With Large Language Models
	Hu, Zhikui 1; Zi, Kangli 2; Luo, Tianyu 2; Huang, Yuwei 2; Wang, Shi 2
	2026
发表期刊	IEEE ACCESS
ISSN	2169-3536
卷号	14 页码:18718-18729
摘要	In the relation extraction (RE) task, large language models (LLMs) have shown remarkable capabilities in predicting unknown relations, offering significant improvements in efficiency and flexibility over traditional methods. However, the probabilistic nature of the generation process in LLMs may lead to the occurrence of hallucinations, causing inaccurate relation triples to be generated. To mitigate this problem, this paper proposes a novel weakly supervised method, Cross-Attention Contrastive Relation Extraction (CACRE), which aims at detecting erroneous relation triples generated by LLMs and then effectively distinguishing valid ones. The CACRE leverages contrastive learning and cross-attention mechanisms. Specifically, contrastive learning is applied to distinguish between positive and negative relation triples, enhancing the model's feature extraction capability by learning discriminative features. Subsequently, a cross-attention mechanism is employed to capture the semantic associations between texts and triples, thereby improving the model's ability to understand and extract information from the input content. Experiment results on the DuIE2.0 dataset and the TACRED dataset demonstrate that CACRE significantly outperforms baseline LLMs, with average improvements of 12% and 8% in precision, respectively.
关键词	Semantics Contrastive learning Feature extraction Weak supervision Vectors Training Large language models Data mining Tensors Reliability Relation extraction weak supervision contrastive learning LLMs
DOI	10.1109/ACCESS.2026.3660343
收录类别	SCI
语种	英语
WOS研究方向	Computer Science ; Engineering ; Telecommunications
WOS类目	Computer Science, Information Systems ; Engineering, Electrical & Electronic ; Telecommunications
WOS记录号	WOS:001687453200010
出版者	IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
引用统计
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/42798
专题	中国科学院计算技术研究所
通讯作者	Zi, Kangli
作者单位	1.Jiangsu Univ Sci & Technol, Zhenjiang 212100, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, State Key Lab AI Safety, Beijing 100190, Peoples R China
推荐引用方式 GB/T 7714	Hu, Zhikui,Zi, Kangli,Luo, Tianyu,et al. CACRE: A Weakly Supervised Method for Cross-Attention Contrastive Relation Extraction With Large Language Models[J]. IEEE ACCESS,2026,14:18718-18729.
APA	Hu, Zhikui,Zi, Kangli,Luo, Tianyu,Huang, Yuwei,&Wang, Shi.(2026).CACRE: A Weakly Supervised Method for Cross-Attention Contrastive Relation Extraction With Large Language Models.IEEE ACCESS,14,18718-18729.
MLA	Hu, Zhikui,et al."CACRE: A Weakly Supervised Method for Cross-Attention Contrastive Relation Extraction With Large Language Models".IEEE ACCESS 14(2026):18718-18729.