江汉大学学报（自然科学版）2026，Vol.54Issue(3)：5-14,10.DOI:10.16389/j.cnki.cn42-1737/n.2026.03.001
模型微调与RAG的爆破领域智能问答系统研究
Research on an Intelligent Question-Answering System for the Blasting Domain Based on Model Fine-Tuning and RAG
摘要
Abstract
To address the triple demands of accuracy,timeliness,and safety compliance in knowledge question-answering for the blasting domain,this paper proposes the BlastRAG system,which integrates model fine-tuning with safety-enhanced retrieval.The system performs automated knowledge structuring to convert literature,such as the Blasting Safety Regulations,into high-quality datasets and a vector knowledge base.Furthermore,Low-Rank Adaptation(LoRA)technology is employed to inject domain-specific knowledge into the Qwen model through fine-tuning.At the retrieval stage,an enhanced architecture combining hybrid retrieval and a Safety Criticality Re-ranker(SCR)is designed.This mechanism prioritizes official safety regulations by assigning them higher weights,thereby fundamentally ensuring the compliance of generated answers.Experimental results demonstrate that BlastRAG performs effectively in terms of retrieval accuracy and compliance.The safety-enhanced retrieval module achieves an accuracy of 91.8%and an overall F1 score of 89.9%,and the ROUGE metrics of the generated answers are also significantly improved.Examples of model responses and expert evaluations further confirm that the system can generate accurate,professional,and strictly compliant answers,providing a reliable intelligent solution for blasting-related high-risk vertical domains.关键词
智能问答/爆破工程/模型微调/混合检索/安全规范Key words
intelligent question-answering/blasting engineering/model fine-tuning/hybrid retrieval/safety regulations分类
信息技术与安全科学引用本文复制引用
吕浩源,兰慧,徐子璎,孙金山..模型微调与RAG的爆破领域智能问答系统研究[J].江汉大学学报（自然科学版）,2026,54(3):5-14,10.基金项目
湖北省自然科学基金面上项目(2024AFB1008) （2024AFB1008）
武汉市科技计划项目(2024050802030155) （2024050802030155）
2024年楚天英才计划科技创新团队项目 （）
