动态检索提升大模型生成质量，让问答更准更稳。
Context-Guided Dynamic Retrieval for Improving Generation Quality in RAG Models
- 根据上下文状态动态调整知识检索，实现端到端优化
- 在Natural Questions上提升BLEU和ROUGE-L得分，效果显著
- 适合需要精准知识融合的复杂生成任务，如多文档问答
本文聚焦于检索增强生成（RAG）架构的动态优化，提出一种状态感知的动态知识检索机制，以提升大语言模型在开放域问答与复杂生成任务中的语义理解与知识调度效率。方法引入多层次感知检索向量构建策略和可微文档匹配路径，实现检索与生成模块的端到端联合训练与协同优化，有效克服静态RAG结构在上下文适应与知识获取方面的局限。在Natural Questions数据集上，对GPT-4、GPT-4o和DeepSeek等多个大模型进行了全面评估。从多个角度开展的对比与消融实验表明，该方法在BLEU和ROUGE-L指标上均有显著提升。同时，在存在语义歧义与多文档融合的任务中表现出更强的鲁棒性与生成一致性。结果凸显其在构建高质量语言生成系统中的广泛应用潜力与实用价值。
原文摘要 · Abstract (English)
This paper focuses on the dynamic optimization of the Retrieval-Augmented Generation (RAG) architecture. It proposes a state-aware dynamic knowledge retrieval mechanism to enhance semantic understanding and knowledge scheduling efficiency in large language models for open-domain question answering and complex generation tasks. The method introduces a multi-level perceptive retrieval vector construction strategy and a differentiable document matching path. These components enable end-to-end joint training and collaborative optimization of the retrieval and generation modules. This effectively addresses the limitations of static RAG structures in context adaptation and knowledge access. Experiments are conducted on the Natural Questions dataset. The proposed structure is thoroughly evaluated across different large models, including GPT-4, GPT-4o, and DeepSeek. Comparative and ablation experiments from multiple perspectives confirm the significant improvements in BLEU and ROUGE-L scores. The approach also demonstrates stronger robustness and generation consistency in tasks involving semantic ambiguity and multi-document fusion. These results highlight its broad application potential and practical value in building high-quality language generation systems.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。