让大模型自己决定何时查资料，提升问答效率与准确率
Self-Routing RAG: Binding Selective Retrieval with Knowledge Verbalization
- 将检索选择视为知识源决策，把模型自身也当作可选知识源
- 在四个基准上平均提升8.5%准确率，检索次数减少21%-40%
- 无需调参即可平衡速度与精度，适合实际部署场景
选择性检索旨在通过在大语言模型（LLM）的参数化知识已足够时跳过外部检索，提升检索增强生成（RAG）的效率与可靠性。然而现有方法受限于二元设计：要么从单一外部源检索，要么跳过检索直接由模型生成答案。本文认为这种回退机制低估了模型的知识能力，且忽视了实际系统中更普遍的多源决策问题。为此提出Self-Routing RAG（SR-RAG），将选择性检索建模为知识源选择，并将LLM本身作为第一类知识源。SR-RAG在单次从左到右生成过程中学习选择合适知识源，可选地对参数化知识进行语义化表达，并基于选定源作答。进一步通过结合基于LLM的不确定性与灵活的外部策略数据存储，提升决策校准能力。在四个基准和三款7B级LLM上，SR-RAG相较强基线提升8.5%/2.1%/4.7%准确率，同时减少26%/40%/21%的检索次数，实现优异的准确率-延迟权衡，且无需针对数据集调整阈值。
原文摘要 · Abstract (English)
Selective retrieval aims to make retrieval-augmented generation (RAG) more efficient and reliable by skipping retrieval when an LLM's parametric knowledge suffices. Despite promising results, existing methods are constrained by a binary design choice: either retrieve from a single external source or skip retrieval and let the LLM directly produce the final answer. We argue that this fallback underestimates the model's knowledge and obscures the more general multi-source decision problem that arises in practical systems. We propose Self-Routing RAG (SR-RAG), which casts selective retrieval as knowledge source selection and treats the LLM itself as a first-class knowledge source. SR-RAG learns to select an appropriate knowledge source, optionally verbalize parametric knowledge, and answer using the selected source, all within a single left-to-right generation pass. SR-RAG further augments source selection by combining LLM-based uncertainty with a flexible external policy datastore to improve decision calibration. Across four benchmarks and three 7B-class LLMs, SR-RAG outperforms a strong selective retrieval baseline by 8.5%/2.1%/4.7% while performing 26%/40%/21% fewer retrievals, and it achieves favorable accuracy-latency trade-offs without dataset-specific threshold tuning.
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。