CLEAR: A Framework Enabling Large Language Models to Discern Confusing Legal Paragraphs

Most of the existing work focuses on enabling LLMs to leverage legal rules (e.g., law articles) to tackle complex legal reasoning tasks, but largely overlooks their ability to understand legal rules.To better evaluate the LLMs' capabilities in this regard, in this work, we propose a new challenge task: Legal Paragraph Prediction (LPP), which aims to predict the legal paragraph given criminal facts.Moreover, to enhance the legal reasoning ability of LLMs, we propose a novel framework CLEAR, enabling LLMs to analyze legal cases with the guidance of legal rule insights.CLEAR consists of four key components, where the Legal Rules Retriever aims to retrieve legal rule knowledge, and the Rule Insights Generator is used to generate legal insights guiding the LLM's reasoning, then the Case Analyzer analyze the case with the guidance of legal rule insights given criminal facts.Finally, the Legal Reasoner synthesizes the criminal facts, legal rule insights, and analysis results to derive the final decision.By conducting extensive experiments on a real-world dataset, experimental results validate the effectiveness of our proposed model.Our codes and dataset are available at https://github.com/xuqi220/CLEAR. Warning!!! This paper contains discussions of violent criminal activities. Discretion is advised.