Exact Adaptive Hybrid Retrieval Without Fixed Top-L Cutoffs
On the map: Retrieval-augmented generation → Generation and context integration
Abstract (arXiv)
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.
Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Generation and context integration, one of 15 directions in Retrieval-augmented generation. Builds on 8 of its 29 references that are in the map. First posted on arXiv 7 Aug 2026.
Builds on
8 of 29 references.
References · 8
- 2016MS MARCO: A Human Generated MAchine Reading COmprehension Datasetcited by 1,591
- 2021BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Modelscited by 1,225
- 2020Fact or Fiction: Verifying Scientific Claimscited by 546
- 2020Overview of the TREC 2019 deep learning trackcited by 282
- 2021Overview of the TREC 2020 deep learning trackcited by 193
- 2024Faster Learned Sparse Retrieval with Block-Max Pruningcited by 10
- 2023Bridging Dense and Sparse Maximum Inner Product Searchcited by 8
- 2024Know When to Fuse: Investigating Non-English Hybrid Retrieval in the Legal Domaincited by 1
Built on by
Citing papers per year: 2026: 1.
1 paper.
Similar, not cited
Close in wording, no citation either way
- 2026Top-K Is Not a Budget for Hybrid Retrieval ↗
- 2026Scaling Retrieval Augmented Generation with RAG Fusion: Lessons from an Industry Deployment
- 2026Tail-Aware Adaptive-k: Query-Adaptive Context Selection for Retrieval-Augmented Generation
- 2026Sifei at SemEval-2026 Task 8: Hybrid Retrieval and Query Rewriting for Multi-Turn RAG
- 2026BoundaryMORPH: Budgeted Reranking via Active Set Selection for Diffuse Retrieval
- 2026Rethinking the Necessity of Adaptive Retrieval-Augmented Generation through the Lens of Adaptive Listwise Ranking
- 2026ScoreGate: Adaptive Chunk Selection for Retrieval-Augmented Generation via Dual-Score Statistical Fusion
- 2026ReFilter: Improving Robustness of Retrieval-Augmented Generation via Gated Filter