arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2211.03046cs.CLcs.AI
收藏

知识即力量：理解因果关系使法律判决预测模型更具泛化性和鲁棒性

Knowledge is Power: Understanding Causality Makes Legal judgment Prediction Models More Generalizable and Robust

Fudan University（复旦大学）；Johns Hopkins University（约翰斯·霍普金斯大学）；Tsinghua University（清华大学）

Haotian Chen, Lingwei Zhang, Yiran Liu, Fanchao Chen, Yang Yu

阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

AI总结：

本文通过因果结构模型分析法律判决预测模型依赖非因果信息的问题，提出数据层面的CIESAM和模型层面的CASAM两种因果增强方法，在三个法律数据集上取得SOTA性能，证明因果关系是提升模型鲁棒性与泛化性的关键。

摘要：

法律判决预测（LJP）旨在根据事实描述并依照法治原则预测判决结果，可作为法律辅助手段，减轻有限法律从业者的巨大工作负担。现有大多数方法应用各种大规模预训练语言模型（PLMs）在LJP任务上进行微调，以取得持续的改进。然而，我们发现一个事实：最先进（SOTA）模型会根据无关（或非因果）信息做出判决预测。这种对法治原则的违背不仅削弱了模型的鲁棒性和泛化能力，还会导致诸如歧视等严重社会问题。在本文中，我们使用因果结构模型（SCMs）从理论上分析LJP模型如何学习做出决策，以及为什么它们能够在没有学习因果关系的情况下成功通过传统测试范式。根据我们的分析，我们提供了两种分别通过因果关系对数据和模型进行干预的解决方案。具体而言，我们首先通过应用开放信息抽取（OIE）技术来区分非因果信息。然后，我们提出了一种名为因果信息增强采样方法（CIESAM）的方法，以从数据中消除非因果信息。为了验证我们的理论分析，我们进一步提出了另一种方法，使用我们提出的因果感知自注意力机制（CASAM）来引导模型学习法律文本中潜在的因果关系知识。CASAM在学习因果信息方面的置信度高于CIESAM。大量实验结果表明，我们提出的两种方法在三个常用的法律特定数据集上均取得了最先进（SOTA）的性能。CASAM更强的性能进一步证明了因果关系是模型鲁棒性和泛化能力的关键。

英文摘要：

Legal Judgment Prediction (LJP), aiming to predict a judgment based on fact descriptions according to rule of law, serves as legal assistance to mitigate the great work burden of limited legal practitioners. Most existing methods apply various large-scale pre-trained language models (PLMs) finetuned in LJP tasks to obtain consistent improvements. However, we discover the fact that the state-of-the-art (SOTA) model makes judgment predictions according to irrelevant (or non-casual) information. The violation of rule of law not only weakens the robustness and generalization ability of models but also results in severe social problems like discrimination. In this paper, we use causal structural models (SCMs) to theoretically analyze how LJP models learn to make decisions and why they can succeed in passing the traditional testing paradigm without learning causality. According to our analysis, we provide two solutions intervening on data and model by causality, respectively. In detail, we first distinguish non-causal information by applying the open information extraction (OIE) technique. Then, we propose a method named the Causal Information Enhanced SAmpling Method (CIESAM) to eliminate the non-causal information from data. To validate our theoretical analysis, we further propose another method using our proposed Causality-Aware Self-Attention Mechanism (CASAM) to guide the model to learn the underlying causality knowledge in legal texts. The confidence of CASAM in learning causal information is higher than that of CIESAM. The extensive experimental results show that both our proposed methods achieve state-of-the-art (SOTA) performance on three commonly used legal-specific datasets. The stronger performance of CASAM further demonstrates that causality is the key to the robustness and generalization ability of models.

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。

↑