%0 Journal Article
%T 基于检索增强生成与软提示优化的大模型开放域问答方法
LLMs Open-Domain Question Answering Method Based on Retrieval-Augmented Generation and Soft Prompt Optimization
%A 刘浩然
%J Modeling and Simulation
%P 901-913
%@ 2324-870X
%D 2025
%I Hans Publishing
%R 10.12677/mos.2025.144340
%X 针对大语言模型(LLM)在开放域问答任务中长尾知识处理能力不足的问题，本文提出了一种融合检索增强生成(RAG)与软提示优化的新型框架SOFTRAG，旨在提升模型对低频知识的利用效率并缓解传统方法的局限性。研究结合检索增强生成(RAG)与软提示优化技术，并引入基于Perceiver的软提示适配器用于提取关键信息，同时采用LoRAMoE方法实现参数高效微调。在PopQA、TriviaQA、PubHealth和ASQA等数据集上，SOFTRAG框架在准确率、推理精度及泛化能力上均显著超越无检索基线和传统RAG方法。消融实验进一步验证了软提示、检索模块和微调技术对性能提升的关键作用。本研究方法有效平衡了性能与资源开销，显著改善了大模型在处理长尾知识任务中的表现，为开放域问答提供了新的优化思路。
To address the limitations of large language models (LLMs) in handling long-tail knowledge for open-domain question answering tasks, this paper proposes SOFTRAG, a novel framework that integrates Retrieval-Augmented Generation (RAG) with soft prompt optimization. The framework aims to enhance the utilization efficiency of low-frequency knowledge and mitigate the constraints of traditional approaches. The study combines RAG with soft prompt optimization techniques, introducing a Perceiver-based soft prompt adapter for extracting critical information and employing the LoRAMoE method for parameter-efficient fine-tuning. Evaluated on datasets including PopQA, TriviaQA, PubHealth, and ASQA, the SOFTRAG framework demonstrates significant improvements in accuracy, reasoning precision, and generalization capabilities compared to retrieval-free baselines and conventional RAG methods. Ablation experiments further validate the critical contributions of soft prompting, retrieval modules, and fine-tuning techniques to performance enhancement. This approach effectively balances performance with computational resource requirements, substantially improving LLMs’ performance on long-tail knowledge tasks and offering new optimization insights for open-domain question answering.
%K 长尾知识，
%K 检索增强生成，
%K 软提示，
%K 大语言模型
Long-Tail Knowledge
%K Retrieval-Augmented Generation
%K Soft Prompt
%K LLMs
%U http://www.hanspub.org/journal/PaperInformation.aspx?PaperID=113050