# Fine-Tuning Vision-Language Models for Markdown Conversion of Financial Tables in Malaysian Audited Financial Reports

arXiv: https://arxiv.org/abs/2508.05669 · HTML: https://mlsanity.com/paper/2508.05669/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Chart understanding and anomaly detection, one of 16 directions in Multimodal LLMs / vision-language models.
- Builds on 14 of its 26 references that are in the map.
- First posted on arXiv 4 Aug 2025.

## Placed in

- Multimodal LLMs / vision-language models / [Chart understanding and anomaly detection](https://mlsanity.com/mllm/chart-understanding-and-anomaly-detection/)

## Builds on (most cited first, 14 of 14)

- [Microsoft COCO: Common Objects in Context](https://mlsanity.com/paper/1405.0312/) (2014)
- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [LayoutLM: Pre-training of Text and Layout for Document Image Understanding](https://mlsanity.com/paper/1912.13318/) (2019)
- [OCR-free Document Understanding Transformer](https://mlsanity.com/paper/2111.15664/) (2021)
- [Image-based table recognition: data, model, and evaluation](https://mlsanity.com/paper/1911.10683/) (2019)
- [olmOCR: Unlocking Trillions of Tokens in PDFs with Vision Language Models](https://mlsanity.com/paper/2502.18443/) (2025)
- [TableFormer: Table Structure Understanding with Transformers](https://mlsanity.com/paper/2203.01017/) (2022)
- [Complicated Table Structure Recognition](https://mlsanity.com/paper/1908.04729/) (2019)
- [TableNet: Deep Learning model for end-to-end Table detection and Tabular data extraction from Scanned Document Images](https://mlsanity.com/paper/2001.01469/) (2020)
- [Enhancing Financial VQA in Vision Language Models using Intermediate Structured Representations](https://mlsanity.com/paper/2501.04675/) (2025)
- [SynFinTabs: A Dataset of Synthetic Financial Tables for Information and Table Extraction](https://mlsanity.com/paper/2412.04262/) (2024)
- [Enhancing Large Vision-Language Models with Layout Modality for Table Question Answering on Japanese Annual Securities Reports](https://mlsanity.com/paper/2505.17625/) (2025)

## Built on by (most cited first, 1 of 1)

- [A Multistage Extraction Pipeline for Long Scanned Financial Documents: An Empirical Study in Industrial KYC Workflows](https://mlsanity.com/paper/2604.26462/) (2026)

## Abstract (arXiv)

Accurately extracting and representing the structure of tabular data from financial documents remains a critical challenge in document understanding, particularly for regulatory and analytical use cases. This study addresses the complexity of converting financial tables from Malaysian audited financial reports into Markdown format, a task complicated by rotated layouts, multi-level headers, and implicit structural cues. We propose a fine-tuned vision-language model (VLM), based on Qwen2.5-VL-7B, optimized for high-fidelity Markdown generation from document images. Our approach includes a curated dataset of 2,152 image-text pairs with augmentations and a supervised fine-tuning strategy using LoRA. To assess performance, we evaluated our model on 100 out-of-sample tables using a dual framework: a criteria-based LLM-as-a-judge for fine-grained accuracy and our novel Markdown Tree-Edit-Distance-based Similarity (TEDS) metric for holistic structural fidelity. Our model achieves a 92.20% overall accuracy on the criteria-based assessment and a 96.53% Markdown TEDS score. This performance significantly surpasses its Qwen2.5-VL-7B base model, larger-scale VLMs, and specialized reasoning-enabled models. Compared to these self-hosted alternatives, it also significantly reduces inference time. Furthermore, its accuracy exceeds that of widely used proprietary models such as OpenAI's GPT-4o and Gemini 2.5 Flash. These results demonstrate that domain-specific fine-tuning provides an effective and efficient method to bridge the gap between unstructured financial documents and downstream automation, rivalling much larger and more general models without their computational overhead.