# Information Extraction From Fiscal Documents Using LLMs

arXiv: https://arxiv.org/abs/2511.10659 · HTML: https://mlsanity.com/paper/2511.10659/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 16 references that are in the map.
- First posted on arXiv 3 Nov 2025.

## Builds on (most cited first, 4 of 4)

- [Image-based table recognition: data, model, and evaluation](https://mlsanity.com/paper/1911.10683/) (2019)
- [TableBench: A Comprehensive and Complex Benchmark for Table Question Answering](https://mlsanity.com/paper/2408.09174/) (2024)
- [Large Language Model for Table Processing: A Survey](https://mlsanity.com/paper/2402.05121/) (2024)
- [TableEval: A Real-World Benchmark for Complex, Multilingual, and Multi-Structured Table Question Answering](https://mlsanity.com/paper/2506.03949/) (2025)

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

- [CTI2TTP: Evidence-Grounded TTP Extraction from Cyber Threat Intelligence via Diverge-then-Converge Verification](https://mlsanity.com/paper/2605.25836/) (2026)
- [Tabular PDF Information Extraction with Local LLMs and Layout-Aware Parsing: A Reliability Evaluation](https://mlsanity.com/paper/2604.00003/) (2026)
- [EvoTS-Agent: A Self-Evolving LLM Agent for Financial Time Series Change Point Detection](https://mlsanity.com/paper/2608.17933/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have demonstrated remarkable capabilities in text comprehension, but their ability to process complex, hierarchical tabular data remains underexplored. We present a novel approach to extracting structured data from multi-page government fiscal documents using LLM-based techniques. Applied to annual fiscal documents from the State of Karnataka in India (200+ pages), our method achieves high accuracy through a multi-stage pipeline that leverages domain knowledge, sequential context, and algorithmic validation. A large challenge with traditional OCR methods is the inability to verify the accurate extraction of numbers. When applied to fiscal data, the inherent structure of fiscal tables, with totals at each level of the hierarchy, allows for robust internal validation of the extracted data. We use these hierarchical relationships to create multi-level validation checks. We demonstrate that LLMs can read tables and also process document-specific structural hierarchies, offering a scalable process for converting PDF-based fiscal disclosures into research-ready databases. Our implementation shows promise for broader applications across developing country contexts.