强基线基础上，多种重写策略互补能显著提效。
Better Together: Complementary Query Rewriting Under a Strong RAG Baseline
- 用多个重写策略并行检索，不同方法在不同问题上表现互补。
- 企业数据上融合四策略，命中率提升12.5点至51.70。
- 设计智能路由，仅对低置信度查询重写，节省成本近60%。
为提升检索增强生成（RAG），常通过重写用户问题生成多个变体并联合检索。本文在固定强基线（BGE稠密检索、交叉编码器重排序、MMR去重）下，对比四种重写策略（S1-S4）与两个强语言模型基线（HyDE、Query2Doc）在三个数据集（HotpotQA、AmbigNQ、512K文档企业RAG基准）上的表现，采用配对自举显著性检验。结果显示：单独重写仅能与强基线持平；但融合多策略可带来超额收益，因不同方法在不同问题上失效。后验合并四策略（S1+S3+S4+HyDE）使企业数据中HIT@10提升12.5点（51.70 vs 39.22），五策略融合达52.98（+13.8）。预算匹配对照仅捕获约40%增益，证明互补性是主因而非检索预算。在HotpotQA上融合提升1.6–1.8点（p<0.001），接近全方法最优；但在AmbigNQ上反而下降2.4点（优于单个方法，p<0.001），分析其原因。由于重写成本高，模拟评估一种置信度门控路由器，仅当基线顶1得分低时触发重写。该方案在企业数据上实现+4.3的命中率增益，且仅对<40%查询执行重写；自动规避AmbigNQ。下游答案质量评估显示，路由器使F1提升+1.92（p<0.01），成本约为原扩展的40%。结论：将重写视为互补覆盖源，结合成本感知路由，而非替代强基线。
原文摘要 · Abstract (English)
A popular way to improve Retrieval-Augmented Generation (RAG) is to rewrite the user's question into several variants and search with all of them. We test whether this actually helps once the underlying search is already strong. Under one fixed, competitive pipeline (BGE dense retrieval, cross-encoder reranking, and MMR diversification), we compare four query-rewriting strategies (S1-S4) against two strong LLM baselines (HyDE, Query2Doc) on three datasets (HotpotQA, AmbigNQ, and the 512K-document EnterpriseRAG-Bench) over three seeds with paired-bootstrap significance tests. Our headline result is that rewriting alone is at best competitive with a strong baseline, but combining methods yields outsized gains because different strategies fail on different questions. A post-hoc union of four methods (S1+S3+S4+HyDE) improves HIT@10 over the baseline by +12.5 points on enterprise data (51.70 vs 39.22), and a five-method union reaches 52.98 (+13.8). Budget-matched controls capture only ~40% of this gain, confirming that complementarity, not retrieval budget, is the primary driver. On HotpotQA the union adds +1.6 to +1.8 points (p<0.001), saturating the all-method oracle; on AmbigNQ the same fusion hurts (-2.4 below the best solo, p<0.001), and we analyze when and why. Because rewriting is expensive, we evaluate in simulation a confidence-gated router that runs rewriting only when the baseline's own top-1 score is low. It captures about half of the enterprise full-merge gain (+4.3 HIT@10) while paying rewriting cost on <40% of queries, and automatically declines to rewrite on AmbigNQ. A downstream answer-quality evaluation confirms the router improves F1 by +1.92 (p<0.01) at roughly 40% of the expansion cost. In short: treat query rewriting as a complementary coverage source, applied through cost-aware routing, not as a standalone replacement for a strong baseline.
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。