用多源检索与强化学习提升法律量刑预测的准确性和可解释性
Multi-Source Retrieval and Reasoning for Legal Sentencing Prediction
- 基于推理需求动态检索多源法律信息，增强大模型理解力
- 在两个真实数据集上量刑预测准确率显著提升，且过程可解释
- 适合法律AI研究者和司法智能化开发者参考
法律判决预测（LJP）旨在从案件事实中预测司法结果，通常包括法律条文、罪名和量刑预测。尽管近期方法在前两项任务表现良好，但量刑预测（LSP）仍因需精细客观知识与灵活主观推理而困难。为此，我们提出$MSR^2$框架，将多源检索与推理结合大模型，并引入强化学习。$MSR^2$使大模型能根据推理需求进行多源检索，并通过过程级奖励引导中间主观推理步骤。在两个真实世界数据集上的实验表明，$MSR^2$在量刑预测上同时提升了准确率与可解释性，为实用法律AI迈出重要一步。代码已公开于https://github.com/cjj826/MSR2。
原文摘要 · Abstract (English)
Legal judgment prediction (LJP) aims to predict judicial outcomes from case facts and typically includes law article, charge, and sentencing prediction. While recent methods perform well on the first two subtasks, legal sentencing prediction (LSP) remains difficult due to its need for fine-grained objective knowledge and flexible subjective reasoning. To address these limitations, we propose $MSR^2$, a framework that integrates multi-source retrieval and reasoning in LLMs with reinforcement learning. $MSR^2$ enables LLMs to perform multi-source retrieval based on reasoning needs and applies a process-level reward to guide intermediate subjective reasoning steps. Experiments on two real-world datasets show that $MSR^2$ improves both accuracy and interpretability in LSP, providing a promising step toward practical legal AI. Our code is available at https://github.com/cjj826/MSR2.
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。