Metraipolis › archive › dc_de2eaab3c315

RidgeRank: Efficient Visual Document Reranking via Score Fusion and a Shallow Linear Readout — arXiv:2609.34192

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.34192
License (as archived)
CC0-1.0
Archived
2026-10-07T23:49:50.353Z
SHA-256 of the archived text
6edf32743a9c33cdfc71a4da397f7a3f437133430e721758be5fff315b1c9499
Stable URL of this page
https://metraipolis.com/documento/dc_de2eaab3c315

How to cite

RidgeRank: Efficient Visual Document Reranking via Score Fusion and a Shallow Linear Readout — arXiv:2609.34192 — arXiv (en), https://arxiv.org/abs/2609.34192 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_de2eaab3c315 (Metraipolis archive dc_de2eaab3c315, sha256 6edf32743a9c33cdfc71a4da397f7a3f437133430e721758be5fff315b1c9499)
BibTeX
@misc{dcde2eaab3c315,
  title = {RidgeRank: Efficient Visual Document Reranking via Score Fusion and a Shallow Linear Readout — arXiv:2609.34192},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.34192},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_de2eaab3c315; sha256 6edf32743a9c33cdfc71a4da397f7a3f437133430e721758be5fff315b1c9499},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34192. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Multimodal language models rerank visual document retrieval results accurately, but scoring every candidate page at full cost makes them slow. Some methods that compress these rerankers need relevance labels to regain accuracy, and they rank by the reranker score alone. RidgeRank measures how much relevance signal the reranker score lacks and recovers it from the retriever score through a closed-form fusion rule. Maximizing a correlation objective gives the optimal fusion weight, along with the exact condition under which the reranker score by itself cannot reach that optimum. The reranker is further corrected by a single vector applied to an intermediate hidden state, obtained through one centered ridge regression onto the same model's full-depth scores on uncompressed pages. On 12 datasets drawn from ViDoRe 2 and ViDoRe 3, evaluated with two retrievers and two language model backbones, RidgeRank brings NDCG@5 to within 1.2 pp of a full cross encoder with speedups of up to 48 times, advancing the accuracy and latency Pareto frontier for visual document reranking.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-29 in cs.IR).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2609.34192 — 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 2026-10-07T23:26:57.196Z dalla pagina https://arxiv.org/catchup/cs.IR/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).