Metraipolis › archive › dc_250bd18f8d32

Adaptive Sparsity Optimization with Learnable Soft Top-K and Per-Term Thresholding for Efficient Retrieval — arXiv:2610.02572

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.02572
License (as archived)
CC0-1.0
Archived
2026-10-06T09:00:22.865Z
SHA-256 of the archived text
c48679835aac2f007ebe3ddeca8f590eb12d942d8c4edaa011b30f123ad33277
Stable URL of this page
https://metraipolis.com/documento/dc_250bd18f8d32

How to cite

Adaptive Sparsity Optimization with Learnable Soft Top-K and Per-Term Thresholding for Efficient Retrieval — arXiv:2610.02572 — arXiv (en), https://arxiv.org/abs/2610.02572 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_250bd18f8d32 (Metraipolis archive dc_250bd18f8d32, sha256 c48679835aac2f007ebe3ddeca8f590eb12d942d8c4edaa011b30f123ad33277)
BibTeX
@misc{dc250bd18f8d32,
  title = {Adaptive Sparsity Optimization with Learnable Soft Top-K and Per-Term Thresholding for Efficient Retrieval — arXiv:2610.02572},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.02572},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_250bd18f8d32; sha256 c48679835aac2f007ebe3ddeca8f590eb12d942d8c4edaa011b30f123ad33277},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.02572. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent work on neural sparse retrieval has demonstrated strong relevance by leveraging Large Language Models (LLMs) for semantic term expansion. However, learned models paired with previous sparsification techniques still yield overly long document and query vectors partly due to a large LLM vocabulary, imposing a serious challenge to retrieval time and space efficiency. This paper proposes a scheme for optimizing model sparsity through a synergy of adaptive strategies, including learnable soft top-K, per-term thresholding, and FLOPs regularization to increase the sparsity of query and document vectors. Experimental results with Lion-SP model on the MS MARCO and BEIR datasets demonstrate that the proposed scheme can outperform the baselines by significantly reducing the average query and document lengths. Our scheme can achieve much shorter retrieval latency and lower storage cost while maintaining highly competitive relevance.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-10-05 in cs.IR).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2610.02572 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-06T08:21:15.846Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-10-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).