# Comparative Study of Domain-adapted VLMs for General Document Visual Question Answering

arXiv: https://arxiv.org/abs/2607.07179 · HTML: https://mlsanity.com/paper/2607.07179/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 48 references that are in the map.
- First posted on arXiv 8 Jul 2026.

## Builds on (most cited first, 30 of 33)

- [LoRA: Low-Rank Adaptation of Large Language Models](https://mlsanity.com/paper/2106.09685/) (2021)
- [Qwen3-VL Technical Report](https://mlsanity.com/paper/2511.21631/) (2025)
- [InternVL: Scaling up Vision Foundation Models and Aligning for Generic Visual-Linguistic Tasks](https://mlsanity.com/paper/2312.14238/) (2023)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking](https://mlsanity.com/paper/2204.08387/) (2022)
- [LayoutLMv2: Multi-modal Pre-training for Visually-Rich Document Understanding](https://mlsanity.com/paper/2012.14740/) (2020)
- [OCR-free Document Understanding Transformer](https://mlsanity.com/paper/2111.15664/) (2021)
- [SlideVQA: A Dataset for Document Visual Question Answering on Multiple Images](https://mlsanity.com/paper/2301.04883/) (2023)
- [BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents](https://mlsanity.com/paper/2108.04539/) (2021)
- [LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding](https://mlsanity.com/paper/2404.05225/) (2024)
- [MapQA: A Dataset for Question Answering on Choropleth Maps](https://mlsanity.com/paper/2211.08545/) (2022)
- [SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers](https://mlsanity.com/paper/2407.09413/) (2024)
- [Enhancing Visual Document Understanding with Contrastive Learning in Large Visual-Language Models](https://mlsanity.com/paper/2402.19014/) (2024)
- [OmniTab: Pretraining with Natural and Synthetic Data for Few-shot Table-based Question Answering](https://mlsanity.com/paper/2207.03637/) (2022)
- [ICDAR 2021 Competition on Document VisualQuestion Answering](https://mlsanity.com/paper/2111.05547/) (2021)
- [Q: How to Specialize Large Vision-Language Models to Data-Scarce VQA Tasks? A: Self-Train on Unlabeled Images!](https://mlsanity.com/paper/2306.03932/) (2023)
- [Addressing Bias in LLMs: Strategies and Application to Fair AI-based Recruitment](https://mlsanity.com/paper/2506.11880/) (2025)
- [PBa-LLM: Privacy- and Bias-aware NLP using Named-Entity Recognition (NER)](https://mlsanity.com/paper/2507.02966/) (2025)
- [FS-DAG: Few Shot Domain Adapting Graph Networks for Visually Rich Document Understanding](https://mlsanity.com/paper/2505.17330/) (2025)
- [Are Vision-Language Models Ready for Dietary Assessment? Exploring the Next Frontier in AI-Powered Food Image Recognition](https://mlsanity.com/paper/2504.06925/) (2025)
- [Benchmarking Graph Neural Networks for Document Layout Analysis in Public Affairs](https://mlsanity.com/paper/2505.14699/) (2025)
- [Privacy-Aware Detection of Fake Identity Documents: Methodology, Benchmark, and Improved Algorithms (FakeIDet2)](https://mlsanity.com/paper/2508.11716/) (2025)
- [Is My Vision-Language Data in Your AI? Membership Inference Test (MINT) Demo 2](https://mlsanity.com/paper/2606.14748/) (2026)
- [Personalized Weight Loss Management through Wearable Devices and Artificial Intelligence](https://mlsanity.com/paper/2409.08700/) (2024)
- [Evaluating Social Engineering Risks in AI-based Interaction using Biometrics and a Gaming Setup](https://mlsanity.com/paper/2606.17793/) (2026)
- [AttZoom: Attention Zoom for Better Visual Features](https://mlsanity.com/paper/2508.03625/) (2025)
- [Auditing Training Data in Domain-adapted LLMs: LoRA-MINT](https://mlsanity.com/paper/2606.06946/) (2026)
- [Membership Inference Test: Auditing Training Data in Object Classification Models](https://mlsanity.com/paper/2601.12929/) (2026)
- [AIriskEval-edu: New Dataset for Risk Assessment in AI-mediated K-12 Educational Explanations](https://mlsanity.com/paper/2607.01934/) (2026)
- [Document Layout Annotation: Database and Benchmark in the Domain of Public Affairs](https://mlsanity.com/paper/2306.10046/) (2023)

## Built on by (most cited first, 3 of 3)

- [CrimeNER Demo: Named-Entity Recognition in the Crime Domain](https://mlsanity.com/paper/2607.14800/) (2026)
- [AIriskEval-edu Demo: Auditing of Pedagogical Risks in Educational Explanations](https://mlsanity.com/paper/2607.25634/) (2026)
- [inLoRA-MINT: Internal Representations for Auditing Training Data in Domain-adapted LLMs](https://mlsanity.com/paper/2610.18051/) (2026)

## Abstract (arXiv)

Document Visual Question Answering (DocVQA) presents a complex multimodal challenge, requiring models to exploit visual, textual, and layout information from documents. Although Vision-Language Models (VLMs) have shown remarkable performance in text-vision tasks, their robustness and transferability to different document domains remains underexplored. In this study, we present a comprehensive evaluation of 8 open-source pretrained VLMs on DocVQA in three different document domains: industrial documents of varying type, infographics, and presentation slides. We systematically assess model performance under zero-shot evaluations, fully supervised finetuning with inter- and intra-dataset evaluations, and few-shot learning evaluations of knowledge transfer between domains. Our findings demonstrate that while large pretrained VLMs possess strong zero-shot baselines for structured layouts, their performance strongly decreases on visually complex layouts of infographics and slides. Although parameter scaling is a dominant factor on performance, supervised finetuning yields higher relative gains in smaller architectures. Furthermore, our cross-domain and few-shot experiments show that visual understanding is the main bottleneck for DocVQA, not a lack of knowledge from the VLMs. Using 50 target domain samples, the models finetuned in DocVQA with datasets of different domains rapidly adapt to the target domain documents, even surpassing their fully supervised counterparts in some cases.