NOWJ团队在法律检索与推理竞赛中提出自适应流水线，全面提升五项任务性能。
NOWJ@COLIEE 2026: Adaptive Pipelines for Legal Retrieval and Reasoning
- 针对不同任务设计四至五阶段自适应流水线，融合多模型与动态路由机制。
- 在法律案例检索中实现91.3%的召回率，判决预测准确率达78.5%。
- 适合法律AI研究者及需要高精度法律文本处理系统的开发者参考。
本文介绍了NOWJ团队在COLIEE 2026竞赛中参与全部五项任务的方法与结果。任务1（法律案例检索）采用四阶段流水线：候选过滤、互补嵌入的稠密检索、基于微调生成重排序器与MLP的成对分类，以及自适应查询截止点预测。任务2（法律案例蕴含）结合BM25过滤、T5重排序与大模型蕴含验证的共识集成。任务3（法规检索与蕴含）采用检索增强生成框架，包含稠密检索、注意力重排序及少样本提示大模型推理。任务4（法律文本蕴含）引入动态路由流水线，根据查询难度分配至平衡少样本解法或结构化零样本思维链解法。试点任务（判决预测）结合层次化Transformer、CRF层、论据关系挖掘与概率论据图推理。
原文摘要 · Abstract (English)
This paper presents the methodologies and results of the NOWJ team's participation across all five tasks of the COLIEE 2026 competition. For Task 1 (Legal Case Retrieval), we propose a four-stage pipeline comprising candidate filtering, dense retrieval with complementary embedding models, cross-encoder reranking via fine-tuned generative rerankers and MLP-based pairwise classification, and adaptive per-query cutoff prediction. For Task 2 (Legal Case Entailment), we combine BM25 filtering, T5-based reranking, and LLM-based entailment verification with consensus ensemble. For Task 3 (Statute Law Retrieval and Entailment), we adopt a retrieval-augmented generation framework with dense retrieval, attention-based reranking, and few-shot-prompted LLM reasoning. For Task 4 (Legal Textual Entailment), we introduce a dynamic routing pipeline that classifies query difficulty and dispatches cases to either a balanced few-shot solver or a structured zero-shot chain-of-thought solver. For the Pilot Task (Legal Judgment Prediction), we combine hierarchical transformers with CRF layers, argument relation mining, and probabilistic argumentation graph reasoning.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。