Enhancing Judgment Document Generation via Agentic Legal Information Collection and Rubric-Guided Optimization

TL;DR

This paper presents Judge-R1, a framework that improves legal document generation by combining agentic information collection and rubric-guided reinforcement learning, leading to more accurate and logically sound judgment documents.

Contribution

The paper introduces Judge-R1, integrating dynamic legal information retrieval with reinforcement learning to enhance the quality of AI-generated judgment documents.

Findings

Judge-R1 outperforms baselines in legal accuracy.

It achieves higher logical consistency in generated documents.

The framework improves evidence recall and reduces hallucinations.

Abstract

Automating the drafting of judgment documents is pivotal to judicial efficiency, yet it remains challenging due to the dual requirements of comprehensive retrieval of legal information and rigorous logical reasoning. Existing approaches, typically relying on standard Retrieval-Augmented Generation and Supervised Fine-Tuning, often suffer from insufficient evidence recall, hallucinated statutory references, and logically flawed legal reasoning. To bridge this gap, we propose Judge-R1, a unified framework designed to enhance LLM-based judgment document generation by jointly improving legal information collection and judgment document generation. First, we introduce Agentic Legal Information Collection, which employs a dynamic planning agent to retrieve precise statutes and precedents from multiple sources. Second, we implement Rubric-Guided Optimization, a reinforcement learning phase utilizing Group Relative Policy Optimization (GRPO) with a comprehensive legal reward function to enforce adherence to judicial standards and reasoning logic. Extensive experiments on the JuDGE benchmark demonstrate that Judge-R1 significantly outperforms state-of-the-art baselines in both legal accuracy and generation quality.