Intelligent Q&A application of rules and regulations based on large models and RAG technology

Shugang Liu; Yu Zhao

doi:10.54097/jb36az85

Authors

Shugang Liu
Yu Zhao

DOI:

https://doi.org/10.54097/jb36az85

Keywords:

Large Language Model (LLM), Retrieval-augmented Generation (RAG), Optical Character Recognition (OCR), Intelligent question answering system

Abstract

Employees face high learning costs and inefficient retrieval due to the increasing volume and complexity of company rules and regulations. This paper proposes an intelligent Q&A system using OCR, vectorization, Large Language Models (LLM), and Retrieval-Augmented Generation (RAG). We detail the knowledge base construction, prompt engineering, and Q&A module design. Example validation demonstrates the system’s accuracy, completeness, and logical output. Results show it significantly improves employee learning efficiency, offering an innovative solution for rules & regulations informatization.

Downloads

Download data is not yet available.

References

[1] Guan Dianxi, Huang Kun, Cui Nianzhi Research on Survey Geotechnical Q&A Robot Based on Large Model, RAG, and Intelligent Agent Technology [J]. China Survey and Design, 2024 (8): 101-104.

[2] Liu Qian, Yang Xiutong Research on the Application of Large Model Technology in Enterprise Research Project Management: Taking Intelligent Question Answering as an Example [J]. Project Management Technology, 2024, 22 (9): 5-11.

[3] Yan Xiaotong, Tang Xiaobin, Shen Tong, etc Overview of the Development of Large Language Models [J]. Journal of Statistics, 2024, 5 (4): 13-18.

[4] VIDIVELLI S,RAMACHANDRAN M,DHARUNBALAJI A. Efficiency-driven custom chatbot development:Unleashing langchain, RAG, and performance-optimized LLM fusion[ J].Computers, Materials & Continua, 2024, 80(2): 2423-2442.

[5] WANG G ,HE J ,LI H , et al. RAG-leaks: difficulty-calibrated membership inference attacks on retrieval-augmented generation [J].Science China(Information Sciences), 2025, 68(06):23-40.

[6] LEIYB, CAOY, ZHOUTY, etal.Corpus-steered query expansion with large language models [DB/OL]. https: // arxiv.org / abs/2402.18031.2024-2-28.

[7] LEWISP, REREZE, PIKTUSA, etal. Retrieval-augmented generation for knowledge-intensive NLP Tasks [DB/OL]. https://arxiv.org/abs/2005.11401.2020-05-22.