Large Language Models in Legal Systems: A Survey

Abstract This paper provides a comprehensive survey of the role of large language models (LLMs) in legal systems. It examines their applications across key areas such as legal document drafting, case analysis, research, compliance monitoring, and education. In addition to mapping these use cases, the survey reviews datasets and benchmarks that enable the training and fine-tuning of LLMs for legal tasks. The analysis highlights both the opportunities and challenges of adopting LLMs in practice, including issues of bias, interpretability, accuracy, and ethical risk. Particular attention is given to the limitations of current models and the risks of overstating their reliability in high-stakes legal contexts. By synthesizing recent advancements, this paper provides a balanced perspective on the current state of LLMs in the legal domain and outlines future directions for research and practice aimed at improving their effectiveness, accountability, and responsible deployment.