DISC-LawLLM: Fine-tuning Large Language Models for Intelligent Legal Services

TL;DR

DISC-LawLLM is a fine-tuned large language model system designed for providing comprehensive legal services, integrating legal reasoning and retrieval modules to improve accuracy and applicability in the Chinese judicial context.

Contribution

The paper introduces DISC-LawLLM, a novel legal LLM with specialized fine-tuning, legal reasoning, and retrieval capabilities, along with a new benchmark for evaluation.

Findings

Demonstrates effectiveness in diverse legal scenarios

Achieves high scores on the DISC-Law-Eval benchmark

Enhances legal reasoning with retrieval-augmented LLMs

Abstract

We propose DISC-LawLLM, an intelligent legal system utilizing large language models (LLMs) to provide a wide range of legal services. We adopt legal syllogism prompting strategies to construct supervised fine-tuning datasets in the Chinese Judicial domain and fine-tune LLMs with legal reasoning capability. We augment LLMs with a retrieval module to enhance models' ability to access and utilize external legal knowledge. A comprehensive legal benchmark, DISC-Law-Eval, is presented to evaluate intelligent legal systems from both objective and subjective dimensions. Quantitative and qualitative results on DISC-Law-Eval demonstrate the effectiveness of our system in serving various users across diverse legal scenarios. The detailed resources are available at https://github.com/FudanDISC/DISC-LawLLM.