arXiv 2401.153712025-05-01cs.CL

LegalDuet：通过双视图对比学习学习用于法律判决预测的细粒度表示

LegalDuet: Learning Fine-grained Representations for Legal Judgment Prediction via a Dual-View Contrastive Learning

Northeastern University, Shenyang, Liaoning, China（东北大学）；Tsinghua University, Beijing, China（清华大学）；Microsoft Research Asia, Beijing, China（微软亚洲研究院）；Beijing Language and Culture University, Beijing, China（北京语言大学）

Buqiang Xu, Xin Dai, Zhenghao Liu, Huiyuan Xie, Xiaoyuan Yi, Shuo Wang, Yukun Yan, Liner Yang, Yu Gu, Ge Yu

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文提出LegalDuet，一种通过法律案件聚类和法律决策匹配双视图对比学习机制持续预训练语言模型的方法，有效提升了法律判决预测中区分易混淆刑事指控的能力。

摘要：

法律判决预测（LJP）是法律人工智能的一项基础任务，旨在自动预测法律案件的判决结果。现有的LJP模型主要通过对比训练语言模型来识别犯罪事实描述中的法律触发因素。然而，这些LJP模型忽视了学习有效区分判决之间细微差异的重要性，而这对于产生更准确的预测至关重要。在本文中，我们提出了LegalDuet，它持续预训练语言模型以学习一个更定制的嵌入空间来表示法律案件。具体而言，LegalDuet设计了一种双视图机制来持续预训练语言模型：1）法律案件聚类检索相似案件作为困难负样本，并采用对比训练来区分易混淆案件；2）法律决策匹配旨在识别犯罪事实描述中的法律线索，使其与包含正确法律决策的推理链对齐。我们在CAIL2018数据集上的实验证明了LegalDuet的有效性。进一步分析表明，LegalDuet通过减少预测不确定性和增强刑事指控的可分性，提高了预训练语言模型区分易混淆刑事指控的能力。实验表明，LegalDuet产生了一个更集中和可区分的嵌入空间，有效地将犯罪事实与相应的法律决策对齐。代码可在https://github.com/NEUIR/LegalDuet获取。

英文摘要：

Legal Judgment Prediction (LJP) is a fundamental task of legal artificial intelligence, aiming to automatically predict the judgment outcomes of legal cases. Existing LJP models primarily focus on identifying legal triggers within criminal fact descriptions by contrastively training language models. However, these LJP models overlook the importance of learning to effectively distinguish subtle differences among judgments, which is crucial for producing more accurate predictions. In this paper, we propose LegalDuet, which continuously pretrains language models to learn a more tailored embedding space for representing legal cases. Specifically, LegalDuet designs a dual-view mechanism to continuously pretrain language models: 1) Law Case Clustering retrieves similar cases as hard negatives and employs contrastive training to differentiate among confusing cases; 2) Legal Decision Matching aims to identify legal clues within criminal fact descriptions to align them with the chain of reasoning that contains the correct legal decision. Our experiments on the CAIL2018 dataset demonstrate the effectiveness of LegalDuet. Further analysis reveals that LegalDuet improves the ability of pretrained language models to distinguish confusing criminal charges by reducing prediction uncertainty and enhancing the separability of criminal charges. The experiments demonstrate that LegalDuet produces a more concentrated and distinguishable embedding space, effectively aligning criminal facts with corresponding legal decisions. The code is available at https://github.com/NEUIR/LegalDuet.

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。