密集扩展，稀疏锚点：用于混合检索的通道非对称查询扩展
Query Expansion Should Be Coordinated: Dense Expands, Sparse Anchors
- School of Computing and Artificial Intelligence（计算机与人工智能学院）
- Southwest Jiaotong University（西南交通大学）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
本研究提出DESA通道非对称查询扩展方法，在7个BEIR数据集上提升检索指标，同时降低访问深度，为生成段落的通道特定整合及检索效果与访问深度的联合评估提供支撑。
AI中文摘要：
基于大语言模型（LLM）的查询扩展通过生成类文档段落提升检索效果。然而在混合检索中，多数评估采用固定前L个密集排序结果与稀疏排序结果的融合方式。由于截断值既控制跨通道贡献进入融合的范围，又控制各排序结果的访问量，在某一L值下测得的增益可能在另一L值下发生变化甚至反转。我们通过在完整列表融合下评估检索效果，并记录特定策略下各通道的逐通道重放停止深度（即其有序前K个结果可被认证的深度），来分离这些影响。随后我们提出DESA（密集扩展与稀疏锚定），一种通道非对称查询扩展方法：LLM生成互补参考段落；正交残差扩展将这些新语义方向添加到密集查询中，而得分乘积锚定则将它们的词汇线索融入稀疏检索，同时不扩大原始查询的词汇支持范围。在7个BEIR数据集上，DESA相比未扩展查询，nDCG@10提升3.82%，Recall@20提升2.38%，同时将密集和稀疏访问深度分别降低36.90%和36.56%；在数据集权重相等的情况下，63.31%的查询在两个通道中都变得更浅，但在Touché-2020数据集上使用Contriever模型时，两个通道的深度均有所增加。这些结果支持对生成段落进行通道特定整合，并对检索效果与访问深度进行联合评估。
英文摘要：
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%.
