提出DESA方法，让稠密和稀疏检索协同扩展查询，提升效果并降低计算开销。
Query Expansion Should Be Coordinated: Dense Expands, Sparse Anchors
- 共享生成引用，稠密通道扩展语义，稀疏通道锚定原始支持。
- 在7个BEIR数据集上，nDCG@10提升3.82%，Recall@20提升2.38%。
- 减少36.90%稠密与36.56%稀疏的重放停止深度，更高效。
检索增强生成（RAG）系统依赖检索模块为大语言模型输出提供依据。基于LLM的查询扩展通过文档片段丰富检索内容，但现有混合检索评估常将稠密与稀疏排名的前L项固定融合，而L值会影响跨通道贡献和排序访问，从而改变扩张效果的测量。为此，本文评估完整列表有效性，并记录每通道达到有序前K结果所需的重放停止深度。这改变了设计思路：因两种排名共同决定融合结果，其查询构造应协调而非独立设计。本文提出DESA（Dense Expansion and Sparse Anchoring），共享生成参考但差异化整合。正交残差扩展为稠密查询添加新语义方向，分数乘积锚定则在不引入仅扩展匹配的前提下重新排序原始稀疏支持。相同参考发挥互补作用：稠密扩展，稀疏锚定。在7个BEIR数据集上，DESA相较未扩展查询，使nDCG@10提升3.82%，Recall@20提升2.38%，同时降低稠密与稀疏重放停止深度36.90%和36.56%。
原文摘要 · Abstract (English)
Retrieval-augmented generation (RAG) systems rely on retrieval modules to ground large language model (LLM) outputs. LLM-based query expansion enriches retrieval with document-like passages, but evaluations of hybrid retrieval often fuse fixed top-L prefixes of dense and sparse rankings. Because L controls cross-channel contributions and ranking access, it can alter measured expansion gains. We therefore evaluate complete-list effectiveness and record per-channel replay stopping depths required to certify the ordered top-K. This changes the design: because both rankings determine the fused result, their query constructions should be coordinated rather than designed independently. We present DESA (Dense Expansion and Sparse Anchoring), which shares generated references across channels but specializes their integration. Orthogonal residual expansion adds new semantic directions to the dense query, whereas score-product anchoring reorders the original sparse support without admitting expansion-only matches. The same references thus play complementary roles: Dense expands; Sparse anchors. Across seven BEIR datasets, DESA improves nDCG@10 and Recall@20 over the unexpanded query by 3.82% and 2.38%, while reducing dense and sparse replay stopping depths by 36.90% and 36.56%.
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。