# Lightweight and Production-Ready PDF Visual Element Parsing

arXiv: https://arxiv.org/abs/2604.23276 · HTML: https://mlsanity.com/paper/2604.23276/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 13 of its 25 references that are in the map.
- First posted on arXiv 25 Apr 2026.

## Placed in

- Retrieval-augmented generation / [Multimodal RAG](https://mlsanity.com/rag/multimodal-rag/)

## Builds on (most cited first, 13 of 13)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [DocVQA: A Dataset for VQA on Document Images](https://mlsanity.com/paper/2007.00398/) (2020)
- [PubLayNet: largest dataset ever for document layout analysis](https://mlsanity.com/paper/1908.07836/) (2019)
- [DocBank: A Benchmark Dataset for Document Layout Analysis](https://mlsanity.com/paper/2006.01038/) (2020)
- [DocLayout-YOLO: Enhancing Document Layout Analysis through Diverse Synthetic Data and Global-to-Local Adaptive Perception](https://mlsanity.com/paper/2410.12628/) (2024)
- [MMDocIR: Benchmarking Multimodal Retrieval for Long Documents](https://mlsanity.com/paper/2501.08828/) (2025)
- [Benchmarking Retrieval-Augmented Multimodal Generation for Document Question Answering](https://mlsanity.com/paper/2505.16470/) (2025)
- [PDFVQA: A New Dataset for Real-World VQA on PDF Documents](https://mlsanity.com/paper/2304.06447/) (2023)
- [Logo-2K+: A Large-Scale Logo Dataset for Scalable Logo Classification](https://mlsanity.com/paper/1911.07924/) (2019)
- [PDF-MVQA: A Dataset for Multimodal Information Retrieval in PDF-based Visual Question Answering](https://mlsanity.com/paper/2404.12720/) (2024)
- [Multimodal Multi-Hop Question Answering Through a Conversation Between Tools and Efficiently Finetuned Large Language Models](https://mlsanity.com/paper/2309.08922/) (2023)

## Abstract (arXiv)

PDF documents contain critical visual elements such as figures, tables, and forms whose accurate extraction is essential for document understanding and multimodal retrieval-augmented generation (RAG). Existing PDF parsers often miss complex visuals, extract non-informative artifacts (e.g., watermarks, logos), produce fragmented elements, and fail to reliably associate captions with their corresponding elements, which degrades downstream retrieval and question answering. We present a lightweight and production level PDF parsing framework that can accurately detect visual elements and associates captions using a combination of spatial heuristics, layout analysis, and semantic similarity. On popular benchmark datasets and internal product data, the proposed solution achieves ≥96% visual element detection accuracy and 93% caption association accuracy. When used as a preprocessing step for multimodal RAG, it significantly outperforms state-of-the-art parsers and large vision-language models on both internal data and the MMDocRAG benchmark, while reducing latency by over 2×. We have deployed the proposed system in challenging production environment.