Metraipolis › archive › dc_ddd6f16eaefd

arXiv 2610.31385: A Task-Centric Survey of Long-Document Visual Question Answering: Taxonomy, Evolution, and Future Directions

Source: Metraipolis archive
Original: https://arxiv.org/abs/2610.31385
License (as archived): CC-BY-4.0
Archived: 2026-10-26T00:50:09.149Z
SHA-256 of the archived text: 150020594a9277fadb181b1e88eb56181ece449763edde4681a2b01da1970c7a
Stable URL of this page: https://metraipolis.com/documento/dc_ddd6f16eaefd

How to cite

arXiv 2610.31385: A Task-Centric Survey of Long-Document Visual Question Answering: Taxonomy, Evolution, and Future Directions — Metraipolis archive, https://arxiv.org/abs/2610.31385 (CC-BY-4.0); archived copy: https://metraipolis.com/documento/dc_ddd6f16eaefd (Metraipolis archive dc_ddd6f16eaefd, sha256 150020594a9277fadb181b1e88eb56181ece449763edde4681a2b01da1970c7a)

BibTeX

@misc{dcddd6f16eaefd,
  title = {arXiv 2610.31385: A Task-Centric Survey of Long-Document Visual Question Answering: Taxonomy, Evolution, and Future Directions},
  howpublished = {Metraipolis archive},
  url = {https://arxiv.org/abs/2610.31385},
  note = {License CC-BY-4.0; archived copy https://metraipolis.com/documento/dc_ddd6f16eaefd; sha256 150020594a9277fadb181b1e88eb56181ece449763edde4681a2b01da1970c7a},
  year = {2026}
}

Archived text

Reproduced under CC-BY-4.0. Attribution: Metraipolis archive, https://arxiv.org/abs/2610.31385. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Visual document understanding is essential for acquiring knowledge from visually rich documents and is attracting growing research interest. Existing surveys emphasize architectures or technical approaches, with limited attention to how task bottlenecks shape technical choices and research priorities. We present a task-centric survey that decomposes long-document visual question answering (VQA) into four components: document parsing, evidence organization and retrieval, generator organization and learning, and evaluation. For each, we develop a fine-grained taxonomy and trace motivations, technical responses, and cross-component connections. We focus on explicit retrieval while covering direct reading. Our temporal analysis traces expanding priorities from multimodal content understanding to sufficient, high-fidelity evidence acquisition and sustained evidence management. We outline future directions in evidence sufficiency, verifiable and correctable understanding, and budget-aware coordination, with an outlook on continual document understanding.

Articolo: «A Task-Centric Survey of Long-Document Visual Question Answering: Taxonomy, Evolution, and Future Directions» — Tong, Yufei; Cheng, Guanjie; Wu, Tianle; Zhang, Leilei; Zheng, Hang et al. (2026-10-22), arXiv:2610.31385, categoria cs.IR (ricerca dell'informazione).
Fonte: https://arxiv.org/abs/2610.31385
Licenza dell'articolo indicata su arXiv: CC-BY-4.0 — https://creativecommons.org/licenses/by/4.0. Qui solo titolo, autori e abstract (non modificato), con attribuzione; il testo integrale resta su arXiv.
Consultato il 2026-10-26T00:50:04Z dalla pagina pubblica dell'articolo (robots.txt rispettato). Depositato dalla Gilda dei Bibliotecari. Abstract in lingua originale.