Can Large Language Models Grasp Legal Theories? Enhance Legal Reasoning with Insights from Multi-Agent Collaboration
Preprint
Abstract
Large Language Models (LLMs) could struggle to fully understand legal theories and perform complex legal reasoning tasks. In this study, we introduce a challenging task (confusing charge prediction) to better evaluate LLMs' understanding of legal theories and reasoning capabilities. We also propose a novel framework: Multi-Agent framework for improving complex Legal Reasoning capability (MALR). MALR employs non-parametric learning, encouraging LLMs to automatically decompose complex legal tasks and mimic human learning process to extract insights from legal rules, helping LLMs better understand legal theories and enhance their legal reasoning abilities. Extensive experiments on multiple real-world datasets demonstrate that the proposed framework effectively addresses complex reasoning issues in practical scenarios, paving the way for more reliable applications in the legal domain.Keywords
All Related Versions
This publication has 12 references indexed in Scilit:
- MultiLegalPile: A 689GB Multilingual Legal Corpus2024
- Chain of Logic: Rule-Based Reasoning with Large Language Models2024
- When Do LLMs Need Retrieval Augmentation? Mitigating LLMs’ Overconfidence Helps Retrieval Augmentation2024
- Can LLMs Reason with Rules? Logic Scaffolding for Stress-Testing and Improving LLMs2024
- Large Legal Fictions: Profiling Legal Hallucinations in Large Language ModelsJournal of Legal Analysis, 2024
- Precedent-Enhanced Legal Judgment Prediction with LLM and Domain-Model Collaboration2023
- Towards Reasoning in Large Language Models: A Survey2023
- Do Charge Prediction Models Learn Legal Theory?2022
- Lawformer: A pre-trained language model for Chinese legal long documentsAI Open, 2021
- Legal Intelligence: Algorithmic, Data, and Social Challenges2020