JUSTICE: Judicial Unified Synthesis Through Intermediate Conclusion Emulation for Automated Judgment Document Generation

2026-02-09

AI Summary

This study addresses a critical limitation in existing automatic judgment generation methods, which overlook the judicial “pre-judgment” phase, leading to missing legal elements and weak legal reasoning that compromise the rigor of generated rulings. To bridge this gap, the work proposes a novel three-stage framework that explicitly models the judge’s cognitive workflow—“retrieval → pre-judgment → drafting.” The framework comprises a Referential Judicial Element Retriever (RJER) to extract key legal elements, an Intermediate Conclusion Emulator (ICE) to generate intermediate legal conclusions, and a Judicial Unified Synthesizer (JUS) to produce the final judgment document. Evaluated on both in-domain and out-of-domain datasets, the approach significantly outperforms strong baselines, improving sentencing prediction accuracy by 4.6% and demonstrably enhancing legal coherence and factual correctness.

Technology Category

• Natural Language Processing: Generation
• Knowledge Representation and Reasoning: Automated Reasoning and Theorem Proving
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Automated judgment document generation is a significant yet challenging legal AI task. As the conclusive written instrument issued by a court, a judgment document embodies complex legal reasoning. However, existing methods often oversimplify this complex process, particularly by omitting the ``Pre-Judge''phase, a crucial step where human judges form a preliminary conclusion. This omission leads to two core challenges: 1) the ineffective acquisition of foundational judicial elements, and 2) the inadequate modeling of the Pre-Judge process, which collectively undermine the final document's legal soundness. To address these challenges, we propose \textit{\textbf{J}udicial \textbf{U}nified \textbf{S}ynthesis \textbf{T}hrough \textbf{I}ntermediate \textbf{C}onclusion \textbf{E}mulation} (JUSTICE), a novel framework that emulates the ``Search $\rightarrow$ Pre-Judge $\rightarrow$ Write''cognitive workflow of human judges. Specifically, it introduces the Pre-Judge stage through three dedicated components: Referential Judicial Element Retriever (RJER), Intermediate Conclusion Emulator (ICE), and Judicial Unified Synthesizer (JUS). RJER first retrieves legal articles and a precedent case to establish a referential foundation. ICE then operationalizes the Pre-Judge phase by generating a verifiable intermediate conclusion. Finally, JUS synthesizes these inputs to craft the final judgment. Experiments on both an in-domain legal benchmark and an out-of-distribution dataset show that JUSTICE significantly outperforms strong baselines, with substantial gains in legal accuracy, including a 4.6\% improvement in prison term prediction. Our findings underscore the importance of explicitly modeling the Pre-Judge process to enhance the legal coherence and accuracy of generated judgment documents.

Problem

• automated judgment document generation
• Pre-Judge phase
• legal reasoning
• judicial elements
• legal AI

Innovation

• Pre-Judge modeling
• Intermediate conclusion emulation
• Judicial reasoning simulation
• Automated judgment generation
• Legal AI framework