Structured Tender Entities Extraction from Complex Tables with Few-short Learning

Result code in IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F26%3AKY6Z7Q25" target="_blank" >RIV/00216208:11320/26:KY6Z7Q25 - isvavai.cz</a>

Result on the web

<a href="https://aclanthology.org/anthology-files/anthology-files/pdf/regnlp/2025.regnlp-1.pdf#page=71" target="_blank" >https://aclanthology.org/anthology-files/anthology-files/pdf/regnlp/2025.regnlp-1.pdf#page=71</a>

DOI - Digital Object Identifier

—

Result language

angličtina

Original language name

Structured Tender Entities Extraction from Complex Tables with Few-short Learning

Original language description

Extracting structured text from complex tables in PDF tender documents remains a challenging task due to the loss of structural and positional information during the extraction process. AI-based models often require extensive training data, making development from scratch both tedious and time-consuming. Our research focuses on identifying tender entities in complex table formats within PDF documents. To address this, we propose a novel approach utilizing few-shot learning with large language models (LLMs) to restore the structure of extracted text. Additionally, handcrafted rules and regular expressions are employed for precise entity classification. To evaluate the robustness of LLMs with few-shot learning, we employ data-shuffling techniques. Our experiments show that current text extraction tools fail to deliver satisfactory results for complex table structures. However, the few-shot learning approach significantly enhances the structural integrity of extracted data and improves the accuracy of tender entity identification.

Czech name

—

Czech description

—

Type

D - Article in proceedings

CEP classification

—

OECD FORD branch

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Project

—

Continuities

—

Publication year

2025

Confidentiality

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection

Proceedings of the 1st Regulatory NLP Workshop

ISBN

979-8-89176-217-6

ISSN

—

e-ISSN

—

Number of pages

9

Pages from-to

59-67

Publisher name

—

Place of publication

—

Event location

Abu Dhabi, UAE

Event date

Jan 1, 2026

Type of event by nationality

WRD - Celosvětová akce

UT code for WoS article

—