在大型语言模型中实现面向法律判决预测的判别式推理
Enabling Discriminative Reasoning in LLMs for Legal Judgment Prediction
AI总结：
针对LLM难以区分相似法律指控的问题，提出ADAPT判别式推理框架并结合多任务合成轨迹微调，在两个常用数据集上显著提升法律判决预测性能。
摘要：
法律判决预测对于提升司法效率至关重要。在本研究中，我们指出现有大型语言模型（LLM）在该领域表现不佳，原因在于理解案件复杂性以及区分相似指控方面存在挑战。为使LLM适应有效的法律判决预测，我们提出受人类司法推理启发的Ask-Discriminate-Predict（ADAPT）推理框架。ADAPT包括分解案件事实、在潜在指控之间进行判别，以及预测最终判决。我们进一步通过使用多任务合成轨迹进行微调来增强LLM，以在ADAPT框架下提高法律判决预测的准确性和效率。在两个广泛使用的数据集上开展的大量实验表明，我们的框架在法律判决预测中具有优越性能，尤其是在处理复杂且容易混淆的指控时。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
