用替换代替扩展，提升多跳检索生成的精准度
Replace, Don't Expand: Mitigating Context Dilution in Multi-Hop RAG via Fixed-Budget Evidence Assembly
- 不扩写上下文，而是动态替换低相关证据
- 在HotpotQA上准确率提升3-13个百分点
- 适合追求高精度的多跳问答系统开发者
多跳检索增强生成系统常因初始检索遗漏桥梁事实而失效。现有修正方法如Self-RAG、CRAG和Adaptive-$k$多通过增加上下文或修剪列表来应对，但易引发上下文稀释问题。本文提出无需训练的SEAL-RAG控制器，采用‘替换而非扩展’策略，在固定检索深度$k$下对抗稀释。SEAL执行搜索→提取→评估→循环流程：基于实体锚定进行实时提取，构建缺失实体/关系的‘缺口规范’，触发针对性微查询，并通过‘实体优先排序’主动用相关证据替换干扰项。在HotpotQA（$k=3$）和2WikiMultiHopQA（$k=5$）上的实验表明，相较于Self-RAG，SEAL在HotpotQA上提升答案正确率3–13个百分点，证据精确率提升12–18个百分点；在2WikiMultiHopQA上较Adaptive-$k$高出8.0个百分点准确率，同时保持96%的证据精确率，远超CRAG的22%。所有提升均具有统计显著性（$p<0.001$）。通过固定$k$的替换机制，SEAL实现可预测的计算成本，确保前$k$个槽位始终聚焦于精度而非广度。
原文摘要 · Abstract (English)
Retrieval-Augmented Generation (RAG) systems often fail on multi-hop queries when the initial retrieval misses a bridge fact. Prior corrective approaches, such as Self-RAG, CRAG, and Adaptive-$k$, typically address this by \textit{adding} more context or pruning existing lists. However, simply expanding the context window often leads to \textbf{context dilution}, where distractors crowd out relevant information. We propose \textbf{SEAL-RAG}, a training-free controller that adopts a \textbf{``replace, don't expand''} strategy to fight context dilution under a fixed retrieval depth $k$. SEAL executes a (\textbf{S}earch $\rightarrow$ \textbf{E}xtract $\rightarrow$ \textbf{A}ssess $\rightarrow$ \textbf{L}oop) cycle: it performs on-the-fly, entity-anchored extraction to build a live \textit{gap specification} (missing entities/relations), triggers targeted micro-queries, and uses \textit{entity-first ranking} to actively swap out distractors for gap-closing evidence. We evaluate SEAL-RAG against faithful re-implementations of Basic RAG, CRAG, Self-RAG, and Adaptive-$k$ in a shared environment on \textbf{HotpotQA} and \textbf{2WikiMultiHopQA}. On HotpotQA ($k=3$), SEAL improves answer correctness by \textbf{+3--13 pp} and evidence precision by \textbf{+12--18 pp} over Self-RAG. On 2WikiMultiHopQA ($k=5$), it outperforms Adaptive-$k$ by \textbf{+8.0 pp} in accuracy and maintains \textbf{96\%} evidence precision compared to 22\% for CRAG. These gains are statistically significant ($p<0.001$). By enforcing fixed-$k$ replacement, SEAL yields a predictable cost profile while ensuring the top-$k$ slots are optimized for precision rather than mere breadth. We release our code and data at https://github.com/mosherino/SEAL-RAG.
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。