Enabling Discriminative Reasoning in LLMs for Legal Judgment Prediction

TL;DR

This paper proposes the ADAPT reasoning framework to improve large language models' ability to predict legal judgments by decomposing cases, discriminating charges, and fine-tuning with synthetic data, leading to better performance on complex cases.

Contribution

Introduction of the ADAPT framework that enhances LLMs' legal judgment prediction through case decomposition, charge discrimination, and multi-task fine-tuning.

Findings

Superior performance on two datasets, especially with complex charges

Effective case decomposition and charge discrimination improve accuracy

Multi-task synthetic training enhances model efficiency

Abstract

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.