RAG-NoiseLaw A Retrieval-Augmented Framework for Noise Regulation Question

Abstract

As urbanization accelerates, environmental noise pollution poses increasing risks to public health and well-being. However, existing regulatory frameworks are often fragmented and complex, making it difficult for both the public and enforcement agencies to retrieve and interpret relevant information. To address this, this study introduces a retrieval-augmented question-answering system based on the RAG framework, integrating a large language model with a domain-specific knowledge base. The system enhances factual accuracy and contextual relevance by combining semantic retrieval over legal and environmental data with answer generation. Empirical evaluations confirm significant improvements in both retrieval efficiency and response quality, offering a practical tool for interpreting noise regulations.