用历史判例提升欧洲人权法院判决预测准确率
Incorporating Precedents for Legal Judgement Prediction on European Court of Human Rights Cases
- 基于判例相似性检索先例，用交叉注意力融合判例信息
- 训练时融合先例比推理时融合效果更好，稀疏条款下提升显著
- 适合法律AI研究者与司法智能化开发者参考
受判例法（stare decisis）启发，本文探索将历史判例融入法律判决预测（LJP）模型的方法。为提升先例检索精度，训练了一个基于案件中主张条款重叠率的细粒度相关性信号检索器。研究两种集成策略：推理时通过案例相近度进行标签插值，以及训练时通过堆叠交叉注意力模块融合先例。采用检索器与LJP模型联合训练，缓解二者潜在空间差异。在欧洲人权法院（ECHR）管辖范围内的LJP任务上实验表明，训练时融合先例并联合训练检索器与模型，优于仅推理时融合或不使用先例的模型，尤其在条款较少的案件中表现更优。
原文摘要 · Abstract (English)
Inspired by the legal doctrine of stare decisis, which leverages precedents (prior cases) for informed decision-making, we explore methods to integrate them into LJP models. To facilitate precedent retrieval, we train a retriever with a fine-grained relevance signal based on the overlap ratio of alleged articles between cases. We investigate two strategies to integrate precedents: direct incorporation at inference via label interpolation based on case proximity and during training via a precedent fusion module using a stacked-cross attention model. We employ joint training of the retriever and LJP models to address latent space divergence between them. Our experiments on LJP tasks from the ECHR jurisdiction reveal that integrating precedents during training coupled with joint training of the retriever and LJP model, outperforms models without precedents or with precedents incorporated only at inference, particularly benefiting sparser articles.
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。