Debate-Feedback: A Multi-Agent Framework for Efficient Legal Judgment Prediction
This work addresses the need for lightweight and robust AI solutions in legal analysis, offering a novel approach that reduces reliance on large datasets, though it appears incremental in leveraging multi-agent debates.
The paper tackles the problem of legal judgment prediction by proposing a Debate-Feedback framework that integrates LLM multi-agent debate and reliability evaluation, achieving significant efficiency improvements and outperforming existing models in comparative experiments.
The use of AI in legal analysis and prediction (LegalAI) has gained widespread attention, with past research focusing on retrieval-based methods and fine-tuning large models. However, these approaches often require large datasets and underutilize the capabilities of modern large language models (LLMs). In this paper, inspired by the debate phase of real courtroom trials, we propose a novel legal judgment prediction model based on the Debate-Feedback architecture, which integrates LLM multi-agent debate and reliability evaluation models. Unlike traditional methods, our model achieves significant improvements in efficiency by minimizing the need for large historical datasets, thus offering a lightweight yet robust solution. Comparative experiments show that it outperforms several general-purpose and domain-specific legal models, offering a dynamic reasoning process and a promising direction for future LegalAI research.