ASP2LJ : An Adversarial Self-Play Laywer Augmented Legal Judgment Framework

ACL ARR 2025 February Submission6674 Authors

Abstract: Legal Judgment Prediction (LJP) aims to predict judicial outcomes, including relevant legal articles, terms, and fines, leveraging advancements in artificial intelligence and Large Language Models (LLMs). However, despite such progress, LJP faces two key challenges: (1)Data Labeling: Current datasets, derived from authentic cases, suffer from high human annotation costs and imbalanced distributions, leading to model performance degradation. (2)Lawyer's Improvement: Existing systems focus on enhancing judges' decision-making but neglect the critical role of lawyers in refining arguments, which limits overall judicial accuracy. To address these issues, we propose an Adversarial Self-Play Lawyer Augmented Legal Judgment Framework, called ASP2LJ, which integrates a controversy-aware case generation module to tackle long-tailed data distributions and an adversarial self-play mechanism to enhance lawyers' argumentation skills. Our framework enables a judge to reference evolved lawyer's arguments, improving the objectivity, fairness, and rationality of judicial decisions. We also introduce RareCases, a benchmark for rare legal cases in China, and demonstrate the effectiveness of our approach on the SimuCourt dataset. Experimental results show significant improvements, with a 9\% increase in legal article generation accuracy over AgentsCourt and 14\% over GPT-4 on average. Our contributions include a novel integrated framework, a rare-case benchmark, and publicly releasing datasets and code to support further research in automated judicial systems.

Paper Type: Long

Research Area: NLP Applications

Research Area Keywords: NLP Applications

Contribution Types: NLP engineering experiment

Languages Studied: Chinese

Submission Number: 6674