Legal judgment prediction is essential for enhancing judicial efficiency. In this work, we identify that existing large language models (LLMs) underperform in this domain due to challenges in understanding case complexities and distinguishing between similar charges. To adapt LLMs for effective legal judgment prediction, we introduce the Ask-Discriminate-Predict (ADAPT) reasoning framework inspired by human judicial reasoning. ADAPT involves decomposing case facts, discriminating among potential charges, and predicting the final judgment. We further enhance LLMs through fine-tuning with multi-task synthetic trajectories to improve legal judgment prediction accuracy and efficiency under our ADAPT framework. Extensive experiments conducted on two widely-used datasets demonstrate the superior performance of our framework in legal judgment prediction, particularly when dealing with complex and confusing charges.

翻译：法律判决预测对于提升司法效率至关重要。在本研究中，我们发现现有的大型语言模型（LLMs）在此领域表现欠佳，主要源于其理解案件复杂性及区分相似指控方面的挑战。为使LLMs适应高效的法律判决预测任务，我们受人类司法推理过程启发，提出了Ask-Discriminate-Predict（ADAPT）推理框架。该框架包含分解案件事实、区分潜在指控及预测最终判决三个步骤。我们进一步通过多任务合成轨迹对LLMs进行微调，以提升其在ADAPT框架下进行法律判决预测的准确性与效率。在两个广泛使用的数据集上进行的大量实验表明，我们的框架在法律判决预测中表现出优越性能，尤其在处理复杂且易混淆的指控时效果显著。