Metraipolis › archive › dc_efc2ddaad811

Do MLLMs Really Understand Low-Resource Khmer Documents? A Pilot Study on Khmer Document VQA — arXiv:2608.28635

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.28635
License (as archived)
CC0-1.0
Archived
2026-10-17T07:47:10.776Z
SHA-256 of the archived text
5c3888d6bfe2d33bb4e46c59161d0bbee7b41c5d7588d18e90fd1af900a738d0
Stable URL of this page
https://metraipolis.com/documento/dc_efc2ddaad811

How to cite

Do MLLMs Really Understand Low-Resource Khmer Documents? A Pilot Study on Khmer Document VQA — arXiv:2608.28635 — arXiv (en), https://arxiv.org/abs/2608.28635 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_efc2ddaad811 (Metraipolis archive dc_efc2ddaad811, sha256 5c3888d6bfe2d33bb4e46c59161d0bbee7b41c5d7588d18e90fd1af900a738d0)
BibTeX
@misc{dcefc2ddaad811,
  title = {Do MLLMs Really Understand Low-Resource Khmer Documents? A Pilot Study on Khmer Document VQA — arXiv:2608.28635},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.28635},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_efc2ddaad811; sha256 5c3888d6bfe2d33bb4e46c59161d0bbee7b41c5d7588d18e90fd1af900a738d0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.28635. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent multimodal large language models (MLLMs) have advanced document understanding, visual question answering, and text extraction. However, their reliability in low-resource, non-Latin settings remains uncertain. Khmer form documents present particular challenges because they contain complex script forms, mixed Khmer-English fields, and monetary values in both Cambodian Riel and US Dollars. Available resources for Khmer Document VQA are also limited. This paper presents a pilot diagnostic evaluation of open MLLMs on Khmer document images. We construct an evaluation subset from the previously introduced KH-FUNSD collection, covering invoices, receipts, quotations, and other business forms. The subset includes questions in English and Khmer, with answers retained in their original English, Khmer, mixed-script, or numeric forms. Rather than introducing a full public benchmark, this study examines the capabilities and failure modes of existing models. We evaluate representative open Qwen-VL models using direct image-based prompting and compare parser-assisted and external OCR-assisted configurations with Qwen3-VL-8B. Direct Qwen3-VL-8B outperforms smaller models, achieving 51.9% overall accuracy, although performance remains limited for Khmer-script and mixed-script answers. External OCR produces the strongest results, reaching 61.9% with Tesseract and 61.6% with PaddleOCR. Nevertheless, Khmer-script answers remain substantially more difficult than English and numeric fields. The results indicate that current MLLMs can process visually clear English and structured numeric content, but reliable native Khmer document understanding remains an open challenge.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-01 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.28635 — 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 2026-10-17T07:28:26.670Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).