<![CDATA[This study proposes the development of an intelligent Question and Answering (Q&A) system based on Retrieval-Augmented Generation (RAG) and Large Language Models (LLM) to support public statistical services at the Central Bureau of Statistics (BPS) of Empat Lawang Regency. Conventional public information services still rely heavily on manual interactions, which often result in delayed responses, high workload for officers, and inconsistent information delivery. Large Language Models have demonstrated strong natural language understanding capabilities; however, they suffer from hallucination issues when not grounded in authoritative data sources. To address this limitation, the RAG approach is employed by integrating document retrieval mechanisms with generative language models, ensuring that responses are generated based on official statistical documents. This research adopts the CRISP-DM framework as the system development methodology, with evaluation conducted using confusion matrix metrics, including accuracy, precision, recall, and F1-score. The results show that the proposed system is able to deliver accurate, relevant, and context-aware answers to public statistical queries, thereby improving efficiency, accessibility, and reliability of digital public services. ]]>
Copyrights © 2026
