aiqbench analysis
This paper introduces DESA, a method for hybrid retrieval systems that leverages LLM-generated passages to enhance semantic coverage while maintaining lexical precision in sparse channels. By decoupling evaluation metrics from fixed cutoffs, the approach achieves significant gains in recall and ranking quality with reduced computational access depth across multiple datasets. The work highlights critical advancements in optimizing how large language models interact with traditional retrieval architectures for more efficient information access.
Dense Expands, Sparse Anchors: Channel-Asymmetric Query Expansion for Hybrid Retrieval
arXiv:2608.15851v1 Announce Type: cross Abstract: LLM-based query expansion improves retrieval by generating document-like passages. In hybrid retrieval, however, most evaluations fuse fixed top-$L$ dense and sparse rankings. Because the cutoff controls both which cross-channel contributions enter fusion and how much of each ranking is accessed, gains measured at one $L$ can change or reverse at another. We separate these effects by evaluating retrieval effectiveness under complete-list fusion and recording the policy-specific per-channel replay stopping depths at which its ordered top-$K$ is certified. We then introduce DESA (Dense Expansion and Sparse Anchoring), a channel-asymmetric query expansion method. An LLM generates complementary reference passages; orthogonal residual expansion adds their new semantic directions to the dense query, while score-product anchoring incorporates their lexical cues into sparse retrieval without broadening the original query's lexical support. 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 access depths by 36.90% and 36.56%. With equal dataset weighting, 63.31% of queries become shallower in both channels. However, both depths increase with Contriever on Touch\'e-2020. These results support channel-specific integration of generated passages and joint evaluation of retrieval effectiveness and access depth.
Abstract:LLM-based query expansion improves retrieval by generating document-like passages. In hybrid retrieval, however, most evaluations fuse fixed top-$L$ dense and sparse rankings. Because the cutoff controls both which cross-channel contributions enter fusion and how much of each ranking is accessed, gains measured at one $L$ can change or reverse at another. We separate these effects by evaluating retrieval effectiveness under complete-list fusion and recording the policy-specific per-channel replay stopping depths at which its ordered top-$K$ is certified. We then introduce DESA (Dense Expansion and Sparse Anchoring), a channel-asymmetric query expansion method. An LLM generates complementary reference passages; orthogonal residual expansion adds their new semantic directions to the dense query, while score-product anchoring incorporates their lexical cues into sparse retrieval without broadening the original query's lexical support. 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 access depths by 36.90% and 36.56%. With equal dataset weighting, 63.31% of queries become shallower in both channels. However, both depths increase with Contriever on Touché-2020. These results support channel-specific integration of generated passages and joint evaluation of retrieval effectiveness and access depth.
13 pages, 4 figures. Code and artifacts: this https URL
Information Retrieval (cs.IR); Computation and Language (cs.CL)
arXiv:2608.15851 [cs.IR]
(or arXiv:2608.15851v1 [cs.IR] for this version)
https://doi.org/10.48550/arXiv.2608.15851 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 299 words
Related coverage
Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers
Hugging Face · Aug 18, 2026
Welcome Muse Spark Open: open-weight frontier multimodal mixture-of-experts model from Meta
Hugging Face · Oct 15, 2026
SeedER: Seed-Expand-Retrieve for Efficient Knowledge Graph Retrieval
arXiv · Oct 7, 2026
GEM Training: How Meta Doubled the Efficiency of Its LLM-Scale Ads Foundation Model
Meta Engineering · Aug 3, 2026