LegalChainReasoner: A Legal Chain-guided Framework for Criminal Judicial Opinion Generation
This work addresses the need for consistent and practical judicial opinion generation to assist judges and analyze sentencing, though it is incremental as it builds on prior subtask approaches.
The paper tackles the problem of automatically generating criminal judicial opinions by proposing a new task that simultaneously produces legal reasoning and sentencing decisions, and introduces a framework using structured legal chains to guide comprehensive case assessments, achieving superior performance on two Chinese legal case datasets.
A criminal judicial opinion represents the judge's disposition of a case, including the decision rationale and sentencing. Automatically generating such opinions can assist in analyzing sentencing consistency and provide judges with references to similar past cases. However, current research typically approaches this task by dividing it into two isolated subtasks: legal reasoning and sentencing prediction. This separation often leads to inconsistency between the reasoning and predictions, failing to meet real-world judicial requirements. Furthermore, prior studies rely on manually curated knowledge to enhance applicability, yet such methods remain limited in practical deployment. To address these limitations and better align with legal practice, we propose a new LegalAI task: Judicial Opinion Generation, which simultaneously produces both legal reasoning and sentencing decisions. To achieve this, we introduce LegalChainReasoner, a framework that applies structured legal chains to guide the model through comprehensive case assessments. By integrating factual premises, composite legal conditions, and sentencing conclusions, our approach ensures flexible knowledge injection and end-to-end opinion generation. Experiments on two real-world and open-source Chinese legal case datasets demonstrate that our method outperforms baseline models.