Metraipolis › archive › dc_4f773e186ffd

Query-Driven Multimodal Information Extraction from Long Documents — arXiv:2608.22214

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.22214
License (as archived)
CC0-1.0
Archived
2026-10-18T07:41:21.321Z
SHA-256 of the archived text
809863b63ba7ec44f542960dc2a7a35ef61d91a11741c57f68519a08e7130405
Stable URL of this page
https://metraipolis.com/documento/dc_4f773e186ffd

How to cite

Query-Driven Multimodal Information Extraction from Long Documents — arXiv:2608.22214 — arXiv (en), https://arxiv.org/abs/2608.22214 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4f773e186ffd (Metraipolis archive dc_4f773e186ffd, sha256 809863b63ba7ec44f542960dc2a7a35ef61d91a11741c57f68519a08e7130405)
BibTeX
@misc{dc4f773e186ffd,
  title = {Query-Driven Multimodal Information Extraction from Long Documents — arXiv:2608.22214},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.22214},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4f773e186ffd; sha256 809863b63ba7ec44f542960dc2a7a35ef61d91a11741c57f68519a08e7130405},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.22214. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

In domain-specific multimodal long documents, images and text jointly convey complex knowledge that cannot be fully captured by plain text alone. However, existing paradigms like DocVQA primarily focus on generating textual answers or localizing evidence regions, rather than outputting query-specific textual attribute values and corresponding images. To address this gap, we propose query-driven image-text joint extraction from long documents, requiring models to output query-requested textual attribute values and corresponding image bounding boxes. Based on challenges related to both user intent and document content, we designed a two-level taxonomy that operates at the query and instance levels. Further, we construct ITJoint, the first high-quality, manually annotated benchmark for this new task, comprising 2,455 pages of domain-specific documents with numerous non-decorative images, 316 queries, and 910 answer instances. Finally, we evaluate representative standalone Vision-Language Models from different providers and further design Q2IT, a multi-agent collaborative framework consisting of three progressively collaborating agents for evidence collection, page selection, and target-image localization. Using a joint evaluation approach that assesses both text extraction and image localization, our experiments show that standalone VLMs struggle with this task, while Q2IT significantly improves performance on ITJoint, although a substantial gap remains toward perfect results.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Multimedia (cs.MM).
Pagina del lavoro: https://arxiv.org/abs/2608.22214 — 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 2026-10-18T07:37:52.711Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).