Metraipolis › archive › dc_ef3043d2e994

Pre-retrieval Query Clustering for Adaptive Top-k Document Retrieval in RAG Systems — arXiv:2609.13489

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.13489
License (as archived)
CC0-1.0
Archived
2026-10-16T01:48:52.685Z
SHA-256 of the archived text
eae17b1e30fbbea750599a32812a90a6a2a1ff65b52512beac94467be7789e90
Stable URL of this page
https://metraipolis.com/documento/dc_ef3043d2e994

How to cite

Pre-retrieval Query Clustering for Adaptive Top-k Document Retrieval in RAG Systems — arXiv:2609.13489 — arXiv (en), https://arxiv.org/abs/2609.13489 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ef3043d2e994 (Metraipolis archive dc_ef3043d2e994, sha256 eae17b1e30fbbea750599a32812a90a6a2a1ff65b52512beac94467be7789e90)
BibTeX
@misc{dcef3043d2e994,
  title = {Pre-retrieval Query Clustering for Adaptive Top-k Document Retrieval in RAG Systems — arXiv:2609.13489},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.13489},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ef3043d2e994; sha256 eae17b1e30fbbea750599a32812a90a6a2a1ff65b52512beac94467be7789e90},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.13489. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

RAG systems commonly retrieve a fixed number of documents (top-k) to ground generation, but this static approach is brittle: simple queries suffer over-retrieval (adding noise and cost) while complex queries are under-retrieved, causing recall failures that cascade into incorrect answers. Motivated by the question of how many documents must be retrieved to answer an arbitrary query reliably, we propose a practical, general framework for query-adaptive retrieval depth. Offline, we estimate per-query retrieval difficulty by measuring NDCG under the default retriever and deriving a query-specific saturation point k* from the NDCG-k curve. Because computing these signals online is expensive, we cluster a large set of queries in embedding space and summarize each cluster with a recommended retrieval depth that targets high coverage (e.g., ~95%) using a mean-plus-variance rule. At runtime, the system assigns an incoming query to a cluster and selects the corresponding top-k in constant time. Compared with post-retrieval confidence methods that rely on clustering retrieved documents, our approach is pre-retrieval and query-centric, making it robust in heterogeneous, case-like corpora and applicable across domains such as legal, healthcare, finance, and enterprise search. Finally, this framework has been tested in full-traffic queries that improved $F_1$ by over 36% while reducing token usage by 14% on low-complexity clusters without accuracy loss.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-15 in cs.IR).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.13489 — 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 2026-10-16T01:23:14.565Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-15?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).