# Revolutionizing Retrieval-Augmented Generation with Enhanced PDF Structure Recognition

arXiv: https://arxiv.org/abs/2401.12599 · HTML: https://mlsanity.com/paper/2401.12599/

## Key facts

- Cited by 16 papers in the map (data through 14 Oct 2026).
- Placed in RAG robustness and adaptive retrieval, one of 15 directions in Retrieval-augmented generation.
- Builds on 0 of its 9 references that are in the map.
- First posted on arXiv 23 Jan 2024.

## Placed in

- Retrieval-augmented generation / [RAG robustness and adaptive retrieval](https://mlsanity.com/rag/rag-robustness-and-adaptive-retrieval/)

## Built on by (most cited first, 16 of 16)

- [A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.06211/) (2024)
- [MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing](https://mlsanity.com/paper/2509.22186/) (2025)
- [Do LLMs Know to Respect Copyright Notice?](https://mlsanity.com/paper/2411.01136/) (2024)
- [Bring Your Own Knowledge: A Survey of Methods for LLM Knowledge Expansion](https://mlsanity.com/paper/2502.12598/) (2025)
- [AgroLLM: Connecting Farmers and Agricultural Practices through Large Language Models for Enhanced Knowledge Transfer and Practical Application](https://mlsanity.com/paper/2503.04788/) (2025)
- [Optimizing and Evaluating Enterprise Retrieval-Augmented Generation (RAG): A Content Design Perspective](https://mlsanity.com/paper/2410.12812/) (2024)
- [Document Intelligence in the Era of Large Language Models: A Survey](https://mlsanity.com/paper/2510.13366/) (2025)
- [Optimizing RAG Techniques for Automotive Industry PDF Chatbots: A Case Study with Locally Deployed Ollama Models](https://mlsanity.com/paper/2408.05933/) (2024)
- [Prompting Large Language Models with Partial Knowledge for Answering Questions with Unseen Entities](https://mlsanity.com/paper/2508.01290/) (2025)
- [LLMs for Supply Chain Management](https://mlsanity.com/paper/2505.18597/) (2025)
- [Efficient Document Parsing via Parallel Token Prediction](https://mlsanity.com/paper/2603.15206/) (2026)
- [GE-Chat: A Graph Enhanced RAG Framework for Evidential Response Generation of LLMs](https://mlsanity.com/paper/2505.10143/) (2025)
- [Prompt Orchestration Markup Language](https://mlsanity.com/paper/2508.13948/) (2025)
- [Specializing Large Models for Oracle Bone Script Interpretation via Component-Grounded Multimodal Knowledge Augmentation](https://mlsanity.com/paper/2604.06711/) (2026)
- [PDF Retrieval Augmented Question Answering](https://mlsanity.com/paper/2506.18027/) (2025)
- [Qwen Goes Brrr: Off-the-Shelf RAG for Ukrainian Multi-Domain Document Understanding](https://mlsanity.com/paper/2605.10296/) (2026)

## Abstract (arXiv)

With the rapid development of Large Language Models (LLMs), Retrieval-Augmented Generation (RAG) has become a predominant method in the field of professional knowledge-based question answering. Presently, major foundation model companies have opened up Embedding and Chat API interfaces, and frameworks like LangChain have already integrated the RAG process. It appears that the key models and steps in RAG have been resolved, leading to the question: are professional knowledge QA systems now approaching perfection? This article discovers that current primary methods depend on the premise of accessing high-quality text corpora. However, since professional documents are mainly stored in PDFs, the low accuracy of PDF parsing significantly impacts the effectiveness of professional knowledge-based QA. We conducted an empirical RAG experiment across hundreds of questions from the corresponding real-world professional documents. The results show that, ChatDOC, a RAG system equipped with a panoptic and pinpoint PDF parser, retrieves more accurate and complete segments, and thus better answers. Empirical experiments show that ChatDOC is superior to baseline on nearly 47% of questions, ties for 38% of cases, and falls short on only 15% of cases. It shows that we may revolutionize RAG with enhanced PDF structure recognition.