Metraipolis › archive › dc_dbac03cd3e1d

EVIE: Evidence-Vector-Informed Embeddings for Visual Document Retrieval — arXiv:2610.11553

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.11553
License (as archived)
CC0-1.0
Archived
2026-10-09T06:29:59.103Z
SHA-256 of the archived text
81c3c49c82eaa71a6a09188b6fc27ee4d166552161e6ecb3c61b785849b36c6d
Stable URL of this page
https://metraipolis.com/documento/dc_dbac03cd3e1d

How to cite

EVIE: Evidence-Vector-Informed Embeddings for Visual Document Retrieval — arXiv:2610.11553 — arXiv (en), https://arxiv.org/abs/2610.11553 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_dbac03cd3e1d (Metraipolis archive dc_dbac03cd3e1d, sha256 81c3c49c82eaa71a6a09188b6fc27ee4d166552161e6ecb3c61b785849b36c6d)
BibTeX
@misc{dcdbac03cd3e1d,
  title = {EVIE: Evidence-Vector-Informed Embeddings for Visual Document Retrieval — arXiv:2610.11553},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.11553},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_dbac03cd3e1d; sha256 81c3c49c82eaa71a6a09188b6fc27ee4d166552161e6ecb3c61b785849b36c6d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.11553. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Accurate and scalable visual document retrieval (VDR) requires both fine-grained page understanding and efficient indexing, yet existing approaches struggle to achieve both. OCR-based text retrieval adds preprocessing latency and can lose visual and structural cues needed to understand complex pages. Single-vector vision-language models bypass OCR, but compressing an entire page into one vector limits the granularity of query--document matching. Multi-vector retrievers with MaxSim provide finer interactions, yet demand large indexes and still leave room for accuracy improvements. We argue that overcoming these limitations requires preserving query-relevant page evidence throughout representation learning and index construction. To this end, we introduce \textbf{\textit{EVIE}} (Evidence-Vector-Informed Embeddings), a family of native visual document retrievers integrating three key innovations: (1) Evidence-judged data governance, which uses a multimodal judge to identify answer-bearing positives and filter unreliable negatives. (2) Bidirectional teacher--student learning with symmetric listwise distillation and prefix-based Matryoshka representation learning (Prefix-MRL), enabling one student checkpoint to serve six nested embedding dimensions without re-encoding. (3) Hierarchical agglomerative index compression (HAC), which clusters page tokens with spatial regularization and stores semantic centroids for single-stage MaxSim retrieval. Extensive experiments across 138 tasks from ViDoRe V1, V2, V3, and JinaVDR validate EVIE. EVIE-8B achieves 66.75 nDCG@10 on V3, exceeding the best external baseline by 1.43 points, with a four-suite average of 79.51. EVIE-4.5B with HAC retains 59.58 nDCG@10 at only 3.81 GiB per million pages, reducing vector payload by $128\times$. Together, these results improve the accuracy--storage trade-off for visual document retrieval.

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.IR, nuovi lavori del giorno).
Categorie arXiv: Information Retrieval (cs.IR).
Pagina del lavoro: https://arxiv.org/abs/2610.11553 — 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 2026-10-09T05:54:51.499Z dalla pagina https://arxiv.org/list/cs.IR/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).