# Tabular PDF Information Extraction with Local LLMs and Layout-Aware Parsing: A Reliability Evaluation

arXiv: https://arxiv.org/abs/2604.00003 · HTML: https://mlsanity.com/paper/2604.00003/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 12 of its 27 references that are in the map.
- First posted on arXiv 9 Mar 2026.

## Builds on (most cited first, 12 of 12)

- [Large Language Models for Generative Information Extraction: A Survey](https://mlsanity.com/paper/2312.17617/) (2023)
- [Table Meets LLM: Can Large Language Models Understand Structured Table Data? A Benchmark and Empirical Study](https://mlsanity.com/paper/2305.13062/) (2023)
- [LLMParser: An Exploratory Study on Using Large Language Models for Log Parsing](https://mlsanity.com/paper/2404.18001/) (2024)
- [Log Parsing with Prompt-based Few-shot Learning](https://mlsanity.com/paper/2302.07435/) (2023)
- [Log Parsing: How Far Can ChatGPT Go?](https://mlsanity.com/paper/2306.01590/) (2023)
- [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)
- [Exploring the use of a Large Language Model for data extraction in systematic reviews: a rapid feasibility study](https://mlsanity.com/paper/2405.14445/) (2024)
- [Deep Learning based Key Information Extraction from Business Documents: Systematic Literature Review](https://mlsanity.com/paper/2408.06345/) (2024)
- [A Comparative Study on Large Language Models for Log Parsing](https://mlsanity.com/paper/2409.02474/) (2024)
- [Information Extraction From Fiscal Documents Using LLMs](https://mlsanity.com/paper/2511.10659/) (2025)
- [Extracting Complex Named Entities in Legal Documents via Weakly Supervised Object Detection](https://mlsanity.com/paper/2305.05836/) (2023)

## Abstract (arXiv)

Extracting structured information from academic PDF documents is non trivial: a single page typically combines free text metadata with tabular regions, exhibits cross program variation, and is susceptible to Unicode encoding artifacts that interfere with downstream parsing. This study evaluates the reliability of information extraction approaches for tabular PDF documents, using academic course registration documents (Kartu Rencana Studi or KRS) from Indonesian higher education as a case study. Three strategies are compared: LLM only, Hybrid Deterministic - LLM (regex & LLM), and a Camelot based pipeline with LLM fallback. Experiments were conducted on 140 documents for the LLM based test and 860 documents for the Camelot based pipeline evaluation, covering four study programs with varying data in tables and metadata. Three 12 - 14B LLM models (Gemma 3, Phi 4, and Qwen 2.5) were run locally using Ollama and a consumer grade CPU without a GPU. Evaluations used exact match (EM) and Levenshtein similarity (LS) metrics with a threshold of 0.7. Although not applicable to all models, the results show that the hybrid approach can improve efficiency compared to LLM only, especially for deterministic metadata. The Camelot based pipeline with LLM fallback produced the best combination of accuracy (EM and LS up to 0.99 - 1.00) and computational efficiency (less than 1 second per PDF in most cases). The Qwen 2.5:14b model demonstrated the most consistent performance across all scenarios. These findings confirm that integrating deterministic and LLM based methods is a reliable and efficient strategy for information extraction from tabular text based PDF documents in computationally constrained environments.