大模型驱动的科技政策法规问答系统研究OA北大核心CSTPCD

A question-and-answer(Q&A)system for science and technology(S&T)policies and regulations plays a critical role in helping the public understand and apply these regulations.Large language models(LLM)can signifi-cantly enhance the accuracy and efficiency of such systems.However,current LLM-based S&T policy and regula-tion Q&A systems face several challenges:the lack of large-scale,high-quality datasets,insufficient methods for auto-matically constructing datasets with accurate policy and regulation knowledge integration,and issues with the pro-fessional accuracy and timeliness of the models'knowledge updates.To address these challenges,this paper proposes a retrieval-augmented self-prompting method for constructing a high-quality,large-scale S&T policy and regulation Q&A dataset.Additionally,a Q&A system is developed,which combines an LLM optimized by low-rank adaptation(LoRA)techniques with an S&T policy and regulation knowledge base,and employs prompt learning techniques to guide the system in generating accurate answers.Experimental results demonstrate that the constructed Q&A dataset significantly improves the integration of policy and regulation knowledge compared with traditional methods.Fur-thermore,the proposed Q&A system outperforms general LLM-driven systems across various metrics,highlighting its enhanced performance in the domain of S&T policies and regulations.