MeDocVL: A Visual Language Model for Medical Document Understanding and Parsing

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Wang, Wenjie, Wu, Wei, Liu, Ying, Zhao, Yuan, Lv, Xiaole, Diao, Liang, Fan, Zengjian, Xie, Wenfeng, Lin, Ziling, Shi, De, Huang, Lin, Xu, Kaihe, Li, Hong
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866914310569066496
author Wang, Wenjie
Wu, Wei
Liu, Ying
Zhao, Yuan
Lv, Xiaole
Diao, Liang
Fan, Zengjian
Xie, Wenfeng
Lin, Ziling
Shi, De
Huang, Lin
Xu, Kaihe
Li, Hong
author_facet Wang, Wenjie
Wu, Wei
Liu, Ying
Zhao, Yuan
Lv, Xiaole
Diao, Liang
Fan, Zengjian
Xie, Wenfeng
Lin, Ziling
Shi, De
Huang, Lin
Xu, Kaihe
Li, Hong
contents Medical document OCR is challenging due to complex layouts, domain-specific terminology, and noisy annotations, while requiring strict field-level exact matching. Existing OCR systems and general-purpose vision-language models often fail to reliably parse such documents. We propose MeDocVL, a post-trained vision-language model for query-driven medical document parsing. Our framework combines Training-driven Label Refinement to construct high-quality supervision from noisy annotations, with a Noise-aware Hybrid Post-training strategy that integrates reinforcement learning and supervised fine-tuning to achieve robust and precise extraction. Experiments on medical invoice benchmarks show that MeDocVL consistently outperforms conventional OCR systems and strong VLM baselines, achieving state-of-the-art performance under noisy supervision.
format Preprint
id arxiv_https___arxiv_org_abs_2602_06402
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MeDocVL: A Visual Language Model for Medical Document Understanding and Parsing
Wang, Wenjie
Wu, Wei
Liu, Ying
Zhao, Yuan
Lv, Xiaole
Diao, Liang
Fan, Zengjian
Xie, Wenfeng
Lin, Ziling
Shi, De
Huang, Lin
Xu, Kaihe
Li, Hong
Computer Vision and Pattern Recognition
Medical document OCR is challenging due to complex layouts, domain-specific terminology, and noisy annotations, while requiring strict field-level exact matching. Existing OCR systems and general-purpose vision-language models often fail to reliably parse such documents. We propose MeDocVL, a post-trained vision-language model for query-driven medical document parsing. Our framework combines Training-driven Label Refinement to construct high-quality supervision from noisy annotations, with a Noise-aware Hybrid Post-training strategy that integrates reinforcement learning and supervised fine-tuning to achieve robust and precise extraction. Experiments on medical invoice benchmarks show that MeDocVL consistently outperforms conventional OCR systems and strong VLM baselines, achieving state-of-the-art performance under noisy supervision.
title MeDocVL: A Visual Language Model for Medical Document Understanding and Parsing
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2602.06402