Large Language Models in Law: A Survey
Jinqi Lai, Wensheng Gan, Jiayang Wu, Zhenlian Qi, Philip S. Yu
TL;DR
This survey analyzes how large language models can transform law and judiciary, detailing foundational AI technologies, the evolution of LLMs, and the shift from traditional, human-centric judgment to AI-assisted processes. It catalogs current legal LLMs and fine-tuned models, presents an evaluation framework for legal AI, and showcases Law+AI deployment examples across jurisdictions. The authors itemize data-, algorithm-, and practice-related challenges, including data quality, interpretability, bias, and institutional impacts, and propose concrete directions—data infrastructure, model governance, and human-centric integration—to guide future work. Overall, the paper highlights both the promise of AI-enabled efficiency and the need for rigorous standards, transparency, and ethical safeguards in legal AI systems.
Abstract
The advent of artificial intelligence (AI) has significantly impacted the traditional judicial industry. Moreover, recently, with the development of AI-generated content (AIGC), AI and law have found applications in various domains, including image recognition, automatic text generation, and interactive chat. With the rapid emergence and growing popularity of large models, it is evident that AI will drive transformation in the traditional judicial industry. However, the application of legal large language models (LLMs) is still in its nascent stage. Several challenges need to be addressed. In this paper, we aim to provide a comprehensive survey of legal LLMs. We not only conduct an extensive survey of LLMs, but also expose their applications in the judicial system. We first provide an overview of AI technologies in the legal field and showcase the recent research in LLMs. Then, we discuss the practical implementation presented by legal LLMs, such as providing legal advice to users and assisting judges during trials. In addition, we explore the limitations of legal LLMs, including data, algorithms, and judicial practice. Finally, we summarize practical recommendations and propose future development directions to address these challenges.