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

TL;DR

MeDocVL is a specialized vision-language model designed to accurately parse complex medical documents, overcoming noise and layout challenges through innovative training strategies, and outperforming existing OCR and VLM methods.

Contribution

The paper introduces MeDocVL, a novel post-trained vision-language model with training-driven label refinement and noise-aware hybrid post-training for medical document parsing.

Findings

Outperforms conventional OCR systems on medical invoice benchmarks.

Achieves state-of-the-art accuracy under noisy supervision.

Demonstrates robustness to complex layouts and noisy annotations.

Abstract

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.