Retrieval-Augmented Generation in Law: System Paradigms and Optimization across the RAG Pipeline
: The legal domain imposes unique demands on Large Language Models (LLMs), requiring high factual accuracy, precise statutory citation, and transparent reasoning. Retrieval-Augmented Generation (RAG) has emerged as a promising paradigm to mitigate hallucinations and improve knowledge grounding in legal applications. While general RAG systems have achieved success in other domains, legal scenarios present specific challenges due to the complexity of legal language, evolving jurisprudence, and jurisdictional variability. This survey provides a comprehensive overview of the technical evolution of legal RAG systems, categorizing existing approaches into four paradigms: Naive, Advanced, Modular, and Agentic RAG. Drawing on a broad set of recent legal Natural Language Processing (NLP) studies, we organize optimization strategies into three core stages of the RAG pipeline: Pre-retrieval, In-retrieval, and Post-retrieval. These stages highlight techniques adapted to legal use cases, such as document chunking, query rewriting, retrieval control, context filtering, and rationale-based response selection. By highlighting common architectural patterns and legal-specific adaptations, this survey aims to inform future research and practical deployment of robust, interpretable, and trustworthy legal LLMs.