山西大学学报（自然科学版）2026，Vol.49Issue(3)：387-399,13.DOI:10.13451/j.sxu.ns.2025124
基于相向信息增强学习的法条检索
Statute Retrieval Based on Bidirectional Information Enhancement Learning
摘要
Abstract
To address the expression discrepancy between users'vague queries and the professionalism of statutes in statute retrieval,this paper proposes a bidirectional legal information enhancement learning method.By reducing the information gap between que-ries and statutes,this approach eases the model's learning difficulty and improves retrieval performance.On the query side,large lan-guage models are utilized to generate explanatory answers,supplementing missing legal concepts and reasoning logic.On the statute side,an incremental representation is built that incorporates law names,structures,and contents,enhancing the semantic richness of legal texts.Furthermore,by integrating both enhanced query and statute information,the paper designs a hierarchical legal informa-tion-aware contrastive learning framework,enabling precise semantic mapping between user queries and statutes.Experimental re-sults demonstrate that the proposed method significantly improves retrieval performance,increasing Recall@5 from 52.90%to 69.74%and MRR@3 from 47.12%to 63.80%,offering high-quality statute retrieval services for both legal practitioners and large language models.关键词
法条检索/查询增强/大语言模型/对比学习Key words
statute retrieval/query augmentation/large language model/contrastive learning分类
信息技术与安全科学引用本文复制引用
王莅璇,郭冬升,刘泽阳,胡吉坤,周凯,张期磊,张起萌,罗成..基于相向信息增强学习的法条检索[J].山西大学学报（自然科学版）,2026,49(3):387-399,13.基金项目
国家自然科学基金(62502282) （62502282）
山东省重点研发计划(SYS202201) （SYS202201）
泉城省实验室科研项目(QCL20250105) （QCL20250105）
