电子学报2025，Vol.53Issue(9)：3117-3133,17.DOI:10.12263/DZXB.20250656
JURIS:基于理解增强型指令微调的司法命名实体识别方法
JURIS:Judical Understanding-Enhanced Reasoning via Instruction-Tuned Strategies for Named Entity Recognition
摘要
Abstract
Named entity recognition(NER)serves as a fundamental task in the structural analysis and semantic under-standing of legal texts,with the potential to greatly enhance judicial efficiency and promote fairness.However,due to the high complexity and domain specificity of legal language,traditional NER methods struggle to adequately capture contextu-al dependencies in legal documents.They often rely on shallow token-level predictions,lacking both role-based entity inter-pretation and deeper contextual reasoning.These limitations are particularly pronounced when dealing with nested entities,fine-grained entity categories,and ambiguous boundaries that frequently occur in judicial texts.To address these challenges,this paper introduces a novel NER framework for Chinese legal scenarios,termed JURIS(judicial understanding-enhanced reasoning via instruction-tuned strategies for named entity recognition).JURIS reformulates entity recognition as a context-driven conditional generation task and adopts an innovative context-aware embedded annotation strategy,which preserves the original semantic structure of the text while effectively enhancing contextual modeling.In addition,JURIS incorporates a tri-aspect understanding enhancement module(Tri-UEM),consisting of a standardization module,a knowledge-guided module,and an analogy-based learning module.These components jointly strengthen the model's semantic understanding and discrimination ability in the legal domain by improving output consistency,injecting domain-specific knowledge,and enabling contextual analogy transfer.Experimental results demonstrate that JURIS consistently outperforms strong baseline models on multiple datasets,including CAIL2021,Drug,and CSKS2019,achieving state-of-the-art performance.It signifi-cantly improves recognition of nested and fine-grained entities while showing strong generalizability and applicability in do-main-specific information extraction tasks.关键词
司法命名实体识别/理解增强/指令微调/信息抽取Key words
judicial named entity recognition/understanding enhancement/instruction tuning/information extraction分类
信息技术与安全科学引用本文复制引用
彭晗,阮日青,胡颖,刘琼林,张震..JURIS:基于理解增强型指令微调的司法命名实体识别方法[J].电子学报,2025,53(9):3117-3133,17.基金项目
湘江实验室重大项目(No.25XJ01001) Major Project of Xiangjiang Laboratory(No.25XJ01001) （No.25XJ01001）
