不靠训练，用不确定度决定何时检索，双路径选信息更准。
Decide Then Retrieve: A Training-Free Framework with Uncertainty-Guided Triggering and Dual-Path Retrieval
- 根据生成不确定性判断是否需要检索，避免无效调用。
- 双路径检索机制提升稀疏/模糊问题的答对率，平均提升3.2%准确率。
- 无需训练，适配多种模型和检索器，适合部署在资源受限场景。
检索增强生成（RAG）通过引入外部知识提升大语言模型性能，但现有方法盲目触发检索且仅依赖单路径证据构建，常引入噪声并限制效果提升。本文提出无需训练的「决策后检索」（DTR）框架，通过生成不确定性动态判断检索必要性，并设计双路径检索机制与自适应信息选择策略，更好应对稀疏与模糊查询。在五个开放域问答基准、多种模型规模及不同检索器上进行的大量实验表明，DTR在标准RAG和强基线之上持续提升精确匹配（EM）与F1得分，同时减少不必要的检索。代码与数据已公开于https://github.com/ChenWangHKU/DTR。
原文摘要 · Abstract (English)
Retrieval-augmented generation (RAG) enhances large language models (LLMs) by incorporating external knowledge, but existing approaches indiscriminately trigger retrieval and rely on single-path evidence construction, often introducing noise and limiting performance gains. In this work, we propose Decide Then Retrieve (DTR), a training-free framework that adaptively determines when retrieval is necessary and how external information should be selected. DTR leverages generation uncertainty to guide retrieval triggering and introduces a dual-path retrieval mechanism with adaptive information selection to better handle sparse and ambiguous queries. Extensive experiments across five open-domain QA benchmarks, multiple model scales, and different retrievers demonstrate that DTR consistently improves EM and F1 over standard RAG and strong retrieval-enhanced baselines, while reducing unnecessary retrievals. The code and data used in this paper are available at https://github.com/ChenWangHKU/DTR.
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。