Metraipolis › archive › dc_2c574f7ecaa8

PalmLeaf-VQA: A Multi-Script Visual Question Answering Benchmark for Historical Palm-Leaf Manuscript Understanding Across Diverse Regions — arXiv:2609.31651

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.31651
License (as archived)
CC0-1.0
Archived
2026-10-07T20:59:14.800Z
SHA-256 of the archived text
453901fb377c396e5b3ccaee2613778d763193b9f557903e5a5fd8799ccb4f48
Stable URL of this page
https://metraipolis.com/documento/dc_2c574f7ecaa8

How to cite

PalmLeaf-VQA: A Multi-Script Visual Question Answering Benchmark for Historical Palm-Leaf Manuscript Understanding Across Diverse Regions — arXiv:2609.31651 — arXiv (en), https://arxiv.org/abs/2609.31651 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2c574f7ecaa8 (Metraipolis archive dc_2c574f7ecaa8, sha256 453901fb377c396e5b3ccaee2613778d763193b9f557903e5a5fd8799ccb4f48)
BibTeX
@misc{dc2c574f7ecaa8,
  title = {PalmLeaf-VQA: A Multi-Script Visual Question Answering Benchmark for Historical Palm-Leaf Manuscript Understanding Across Diverse Regions — arXiv:2609.31651},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.31651},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2c574f7ecaa8; sha256 453901fb377c396e5b3ccaee2613778d763193b9f557903e5a5fd8799ccb4f48},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.31651. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Historical manuscripts remain largely absent from modern vision-language benchmarks, leaving open how well multimodal large language models (MLLMs) handle culturally diverse, degraded, and non-Latin document images. We introduce \textbf{PalmLeaf-VQA}, a multi-script visual question answering benchmark for historical palm-leaf manuscript understanding across South and Southeast Asian traditions. PalmLeaf-VQA contains \textbf{923 curated manuscript images} and \textbf{7,384 question--answer pairs} from eight collection groups: Balinese, Grantha, Jathakam, Kambaramayanam, Kannada, Khmer, Sundanese, and Tamil. Unlike recognition-oriented resources, the benchmark targets manuscript-aware visual reasoning over preservation-relevant cues, including physical condition, line structure, material and coating, binding holes, margins, symbols, drawings, and localized visual artifacts. We evaluate recent proprietary and open-weight MLLMs under open-answer and constrained-answer prompting and provide fine-grained analysis across collections, question categories, and task types. The strongest evaluated model reaches only \textbf{58.00\% exact-match accuracy} on the held-out test split, revealing substantial limitations in current MLLMs for rare-script, degraded-layout, and preservation-oriented document understanding. PalmLeaf-VQA provides a standardized benchmark for advancing culturally grounded and layout-aware multimodal document analysis.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Computation and Language (cs.CL); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.31651 — 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 2026-10-07T20:29:01.992Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).