面向法律领域的大模型微调与应用

Fine-tuning and application of large language model in law domain

近年来,大语言模型在多个自然语言处理任务上展现出了出色的能力,为智慧法律系统的发展带来巨大的帮助。现有法律领域的大模型,通过微调通用大模型能够实现利用法律知识进行简单的问题回答,即大多以法律咨询问答为主,没有考虑到法律领域的其他使用场景,如法律信息抽取、判决预测等,而真实世界中的法律服务要比对话服务复杂得多。提出中文法律智慧大模型LawLLM,该模型可以面向不同用户群体,提供多样的法律服务。同时,探究了针对法律领域裁判文书的长文本信息抽取的应用。LawLLM在Lawbench上的Zero-shot的平均表现超过了所有对比的大模型,均值比具有175×10^(9)个参数的GPT-3.5-Turbo高0.19%,LawLLM在Lawbench上的Few-shot的平均表现仅次于GPT-3.5-Turbo,相比其低0.02%。

In recent years,large language model have demonstrated outstanding capabilities across multiple natural language processing tasks,greatly aiding the development of intelligent law systems.Existing large language model in the law domain,primarily focuses on fine-tuning foundation model for simple question answering tasks in legal consultation,have not considered other application scenarios in the legal field,such as legal information extraction,judgment prediction,etc.Real world law services are far more complex than dialogues.LawLLM was proposed,a Chinese law intelligent large language model,capable of providing diverse law services for different user groups.Additionally,the application of information extraction on long-context judicial documents in the law domain was explored.The average performance of LawLLM on Lawbench outperforms all the compared large language models,being 0.19%higher than the 175 billion parameter GPT-3.5-Turbo model.LawLLM’s average performance on few-shot tasks on Lawbench is slightly lower than GPT-3.5-Turbo,by 0.02%.