Metraipolis › archive › dc_740feb4543ba
BoundaryMORPH: Budgeted Reranking via Active Set Selection for Diffuse Retrieval — arXiv:2609.27213
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.27213
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T12:27:49.608Z
- SHA-256 of the archived text
a5e913a5efb37714364074ae9820190e0f2130d3a947707e76738d0c45d8704e- Stable URL of this page
https://metraipolis.com/documento/dc_740feb4543ba
How to cite
BoundaryMORPH: Budgeted Reranking via Active Set Selection for Diffuse Retrieval — arXiv:2609.27213 — arXiv (en), https://arxiv.org/abs/2609.27213 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_740feb4543ba (Metraipolis archive dc_740feb4543ba, sha256 a5e913a5efb37714364074ae9820190e0f2130d3a947707e76738d0c45d8704e)
BibTeX
@misc{dc740feb4543ba,
title = {BoundaryMORPH: Budgeted Reranking via Active Set Selection for Diffuse Retrieval — arXiv:2609.27213},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.27213},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_740feb4543ba; sha256 a5e913a5efb37714364074ae9820190e0f2130d3a947707e76738d0c45d8704e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.27213. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Open-ended queries in modern Retrieval-Augmented Generation (RAG) are increasingly "diffuse," requiring a large set of documents to be assembled into a finite LLM context window. To ensure retrieval quality, systems use fast dual-encoders and more expensive cross-encoders (CEs) to score candidates. However, the CE budget $B$ is strictly bounded by latency and is often smaller than the context window capacity $k$. This mismatch makes standard reranking structurally flawed: it wastes compute verifying obvious top candidates while ignoring relevant documents further down the initial ranking. To address this, we introduce BoundaryMORPH, a novel algorithm that allocates CE budget specifically for the LLM's context capacity $k$. Using a Gaussian Process, BoundaryMORPH treats the initial dual-encoder ranking as a structural prior and intelligently spends CE calls on resolving top-$k$ set membership at the boundary, rather than seeking a single most-relevant document. Information from each CE call propagates to unscored documents, maximizing the utility of the budget. We demonstrate that BoundaryMORPH achieves state-of-the-art set retrieval quality across multiple models and datasets with open-ended queries ($+5.4$ nCG@100 over the strongest baseline). Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-24 in cs.IR). Categorie arXiv: Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2609.27213 — 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 2026-10-08T12:11:32.119Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-24?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).