# Empirical Evaluation of PDF Parsing and Chunking for Financial Question Answering with RAG

arXiv: https://arxiv.org/abs/2604.12047 · HTML: https://mlsanity.com/paper/2604.12047/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Legal and financial RAG, one of 15 directions in Retrieval-augmented generation.
- Builds on 20 of its 49 references that are in the map.
- First posted on arXiv 13 Apr 2026.

## Placed in

- Retrieval-augmented generation / [Legal and financial RAG](https://mlsanity.com/rag/legal-and-financial-rag/)

## Builds on (most cited first, 20 of 20)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [ColBERT: Efficient and Effective Passage Search via Contextualized Late Interaction over BERT](https://mlsanity.com/paper/2004.12832/) (2020)
- [YOLOX: Exceeding YOLO Series in 2021](https://mlsanity.com/paper/2107.08430/) (2021)
- [FinQA: A Dataset of Numerical Reasoning over Financial Data](https://mlsanity.com/paper/2109.00122/) (2021)
- [Wizard of Wikipedia: Knowledge-Powered Conversational agents](https://mlsanity.com/paper/1811.01241/) (2018)
- [LLMs-as-Judges: A Comprehensive Survey on LLM-based Evaluation Methods](https://mlsanity.com/paper/2412.05579/) (2024)
- [Ragas: Automated Evaluation of Retrieval Augmented Generation](https://mlsanity.com/paper/2309.15217/) (2023)
- [TAT-QA: A Question Answering Benchmark on a Hybrid of Tabular and Textual Content in Finance](https://mlsanity.com/paper/2105.07624/) (2021)
- [Multilingual E5 Text Embeddings: A Technical Report](https://mlsanity.com/paper/2402.05672/) (2024)
- [FinanceBench: A New Benchmark for Financial Question Answering](https://mlsanity.com/paper/2311.11944/) (2023)
- [FinBERT: A Pretrained Language Model for Financial Communications](https://mlsanity.com/paper/2006.08097/) (2020)
- [Evaluation of Retrieval-Augmented Generation: A Survey](https://mlsanity.com/paper/2405.07437/) (2024)
- [On The Computational Complexity of Self-Attention](https://mlsanity.com/paper/2209.04881/) (2022)
- [MultiHiertt: Numerical Reasoning over Multi Hierarchical Tabular and Textual Data](https://mlsanity.com/paper/2206.01347/) (2022)
- [RAGBench: Explainable Benchmark for Retrieval-Augmented Generation Systems](https://mlsanity.com/paper/2407.11005/) (2024)
- [SPLADE-v3: New baselines for SPLADE](https://mlsanity.com/paper/2403.06789/) (2024)
- [Retrieval Augmented Generation Evaluation in the Era of Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2504.14891/) (2025)
- [A Benchmark of PDF Information Extraction Tools using a Multi-Task and Multi-Domain Evaluation Framework for Academic Documents](https://mlsanity.com/paper/2303.09957/) (2023)
- [A Comparative Study of PDF Parsing Tools Across Diverse Document Categories](https://mlsanity.com/paper/2410.09871/) (2024)

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

- [Industrial-Instruction: An End-to-End Framework for Building Instruction-Tuning and Benchmark Datasets from Industrial Technical Reports](https://mlsanity.com/paper/2608.22817/) (2026)

## Abstract (arXiv)

PDF files are primarily intended for human reading rather than automated processing. In addition, the heterogeneous content of PDFs, such as text, tables, and images, poses significant challenges for parsing and information extraction. To address these difficulties, both practitioners and researchers are increasingly developing new methods, including the promising Retrieval-Augmented Generation (RAG) systems to automated PDF processing. However, there is no comprehensive study investigating how different components and design choices affect the performance of a RAG system for understanding PDFs. In this paper, we propose such a study (1) by focusing on Question Answering, a specific language understanding task, and (2) by leveraging two benchmarks from the financial domain, including TableQuest, our newly generated, publicly available benchmark. We systematically examine multiple PDF parsers and chunking strategies (with varied overlap), along with their potential synergies in preserving document structure and ensuring answer correctness. Overall, our results offer practical guidelines for building robust RAG pipelines for PDF understanding.