Debate-Feedback: A Multi-Agent Framework for Efficient Legal Judgment Prediction
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912314220871680 |
|---|---|
| author | Chen, Xi Mao, Mao Li, Shuo Shangguan, Haotian |
| author_facet | Chen, Xi Mao, Mao Li, Shuo Shangguan, Haotian |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_05358 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Debate-Feedback: A Multi-Agent Framework for Efficient Legal Judgment Prediction Chen, Xi Mao, Mao Li, Shuo Shangguan, Haotian Multiagent Systems Artificial Intelligence 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. |
| title | Debate-Feedback: A Multi-Agent Framework for Efficient Legal Judgment Prediction |
| topic | Multiagent Systems Artificial Intelligence |
| url | https://arxiv.org/abs/2504.05358 |