提出自适应混合检索机制，精准匹配完整列表结果且无需预设召回上限。
Exact Adaptive Hybrid Retrieval Without Fixed Top-L Cutoffs
- 以完整列表加权RRF排序为目标，动态调整每请求的检索深度。
- 在150个查询-快照组合中100%复现完整列表Top-20结果。
- 适合对结果精确性要求高、容忍个别查询变慢的生产系统使用。
现代检索增强生成系统常固定取密集与稀疏检索器的前L项进行融合，将后续贡献视为零。但截断融合并不等价于完整列表融合：未读项可能改变Top-K成员或顺序，即使已包含所有完整列表中的项。因通道排名随查询和语料更新而变化，基于历史查询选定的深度难以可靠迁移。本文提出精确自适应混合检索（EAHR），以完整列表加权RRF定义的有序Top-K为检索目标，将通道深度作为请求级执行状态。每向量标量量化（PVS）和张贴块最大值（PBM）实现可恢复的精确密集与稀疏排序。融合机制限制未读贡献，并仅在可能影响Top-K时请求更多排名。每次成功请求均等效于完整列表融合，无需预设Top-L；否则安全执行至列表耗尽。在五个测试集合及五个时间语料快照上，完整列表加权RRF保持竞争力，而固定深度无法可靠迁移。EAHR在全部150个查询-快照组合中复现了完整列表的有序Top-20。在暖缓存、交错、顺序平衡协议下，批量穷尽执行与EAHR的配对几何平均延迟比分别为23.35（TREC-DL 2019）和30.28（TREC-DL 2020）。反相关排名导致两列表耗尽，部分难题查询在EAHR下更慢。EAHR不保证每个请求都加速；其核心是固定精确结果，同时根据当前排名自适应执行深度。
原文摘要 · Abstract (English)
Modern retrieval-augmented generation (RAG) systems often fuse fixed Top-$L$ results from dense and sparse retrievers, treating later contributions as zero. The cutoff therefore determines both the ranking and its execution cost. Yet truncated fusion is not generally equivalent to complete-list fusion: unread cross-list ranks can change Top-$K$ membership or order even when the observed candidates contain every item in the complete-list Top-$K$. Because channel rankings vary across queries and corpus updates, a depth selected from historical queries may not transfer reliably. We propose Exact Adaptive Hybrid Retrieval (EAHR), which fixes the ordered Top-$K$ defined by complete-list weighted RRF as the retrieval target and treats channel depth as request-specific execution state. Per-Vector Scalar Quantization (PVS) and Posting Block-Max (PBM) produce resumable exact dense and sparse rankings. Fusion bounds unread contributions and requests further ranks only while they can change the Top-$K$. Every successful request therefore matches complete-list fusion without a preset Top-$L$; otherwise, execution continues safely to list exhaustion. Across five test collections and five temporal corpus snapshots, complete-list weighted RRF remained competitive, whereas fixed depths selected from historical queries did not transfer reliably. EAHR reproduced the complete-list ordered Top-20 in all 150 query-snapshot combinations. Under a warm-cache, interleaved, order-balanced protocol, the paired geometric-mean latency ratios of exhaustive batch execution to EAHR were 23.35 on TREC-DL 2019 and 30.28 on TREC-DL 2020. Anti-correlated rankings exhausted both lists, and some difficult queries were slower with EAHR. EAHR does not guarantee a speedup for every request; it fixes the exact result while adapting execution depth to the current rankings.
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。