arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2509.08025cs.CLcs.AI

NOWJ@COLIEE 2025:集成嵌入模型与大型语言模型的多阶段框架用于法律检索与蕴含

NOWJ@COLIEE 2025: A Multi-stage Framework Integrating Embedding Models and Large Language Models for Legal Retrieval and Entailment

VNU University of Engineering and Technology(越南工程大学);Japan Advanced Institute of Science and Technology(日本先进科学研究院);Center for Juris-Informatics, ROIS-DS(法律信息中心,ROIS-DS);Research and Development Center for Large Language Models, NII(大型语言模型研发中心,NII)

Hoang-Trung Nguyen, Tan-Minh Nguyen, Xuan-Bach Le, Tuan-Kiet Le, Khanh-Huyen Nguyen, Ha-Thanh Nguyen, Thi-Hai-Yen Vuong, Le-Minh Nguyen

AI总结:

本文提出一个集成BM25、BERT、BGE-m3及Qwen-2等模型的多阶段框架,在COLIEE 2025法律检索与蕴含任务中获任务2第一名(F1=0.3195),验证了混合检索与生成模型的优势。

摘要:

本文介绍了NOWJ团队在COLIEE 2025竞赛中参与全部五项任务的方法和结果,重点强调了法律案件蕴含任务(任务2)的进展。我们的综合方法系统地集成了预排序模型(BM25、BERT、monoT5)、基于嵌入的语义表示(BGE-m3、LLM2Vec)以及先进的大型语言模型(Qwen-2、QwQ-32B、DeepSeek-V3),用于摘要生成、相关性评分和上下文重排序。具体而言,在任务2中,我们的两阶段检索系统结合了词汇-语义过滤与上下文LLM分析,以F1分数0.3195获得第一名。此外,在其他任务中——包括法律案件检索、成文法检索、法律文本蕴含和法律判决预测——我们通过精心设计的集成和有效的基于提示的推理策略展示了稳健的性能。我们的研究结果凸显了将传统信息检索技术与当代生成模型相结合的混合模型的潜力,为未来法律信息处理的进展提供了有价值的参考。

英文摘要:

This paper presents the methodologies and results of the NOWJ team's participation across all five tasks at the COLIEE 2025 competition, emphasizing advancements in the Legal Case Entailment task (Task 2). Our comprehensive approach systematically integrates pre-ranking models (BM25, BERT, monoT5), embedding-based semantic representations (BGE-m3, LLM2Vec), and advanced Large Language Models (Qwen-2, QwQ-32B, DeepSeek-V3) for summarization, relevance scoring, and contextual re-ranking. Specifically, in Task 2, our two-stage retrieval system combined lexical-semantic filtering with contextualized LLM analysis, achieving first place with an F1 score of 0.3195. Additionally, in other tasks--including Legal Case Retrieval, Statute Law Retrieval, Legal Textual Entailment, and Legal Judgment Prediction--we demonstrated robust performance through carefully engineered ensembles and effective prompt-based reasoning strategies. Our findings highlight the potential of hybrid models integrating traditional IR techniques with contemporary generative models, providing a valuable reference for future advancements in legal information processing.

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。

↑