InternLM-Law: An Open Source Chinese Legal Large Language Model

TL;DR

InternLM-Law is a specialized Chinese legal large language model trained on a large, high-quality legal dataset, achieving top performance on legal benchmarks and aiding future legal AI research.

Contribution

The paper introduces InternLM-Law, a novel two-stage fine-tuning approach and a large legal dataset, advancing Chinese legal LLM capabilities beyond existing models.

Findings

Achieves highest average performance on LawBench

Outperforms GPT-4 on 13 out of 20 subtasks

Provides publicly available legal LLM and dataset

Abstract

While large language models (LLMs) have showcased impressive capabilities, they struggle with addressing legal queries due to the intricate complexities and specialized expertise required in the legal field. In this paper, we introduce InternLM-Law, a specialized LLM tailored for addressing diverse legal queries related to Chinese laws, spanning from responding to standard legal questions (e.g., legal exercises in textbooks) to analyzing complex real-world legal situations. We meticulously construct a dataset in the Chinese legal domain, encompassing over 1 million queries, and implement a data filtering and processing pipeline to ensure its diversity and quality. Our training approach involves a novel two-stage process: initially fine-tuning LLMs on both legal-specific and general-purpose content to equip the models with broad knowledge, followed by exclusive fine-tuning on high-quality legal data to enhance structured output generation. InternLM-Law achieves the highest average performance on LawBench, outperforming state-of-the-art models, including GPT-4, on 13 out of 20 subtasks. We make InternLM-Law and our dataset publicly available to facilitate future research in applying LLMs within the legal domain.