Evaluation of LLM-Based Strategies for the Extraction of Food Product Information from Online Shops

Christoph Brosch, Sian Brumm, Rolf Krieger, Jonas Scheffler

2025

Abstract

Generative AI and large language models (LLMs) offer significant potential for automating the extraction of structured information from web pages. In this work, we focus on food product pages from online retailers and explore schema-constrained extraction approaches to retrieve key product attributes, such as ingredient lists and nutrition tables. We compare two LLM-based approaches, direct extraction and indirect extraction via generated functions, evaluating them in terms of accuracy, efficiency, and cost on a curated dataset of 3,000 food product pages from three different online shops. Our results show that although the indirect approach achieves slightly lower accuracy (96.48%, −2.27% compared to direct extraction), it reduces the number of required LLM calls by 95.82%, leading to substantial efficiency gains and lower operational costs. These findings suggest that indirect extraction approaches can provide scalable and cost-effective solutions for large-scale information extraction tasks from template-based web pages using LLMs.

Paper Citation

in Harvard Style

Brosch C., Brumm S., Krieger R. and Scheffler J. (2025). Evaluation of LLM-Based Strategies for the Extraction of Food Product Information from Online Shops. In Proceedings of the 14th International Conference on Data Science, Technology and Applications - Volume 1: DATA; ISBN 978-989-758-758-0, SciTePress, pages 709-715. DOI: 10.5220/0013647300003967

in Bibtex Style

@conference{data25,
author={Christoph Brosch and Sian Brumm and Rolf Krieger and Jonas Scheffler},
title={Evaluation of LLM-Based Strategies for the Extraction of Food Product Information from Online Shops},
booktitle={Proceedings of the 14th International Conference on Data Science, Technology and Applications - Volume 1: DATA},
year={2025},
pages={709-715},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0013647300003967},
isbn={978-989-758-758-0},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 14th International Conference on Data Science, Technology and Applications - Volume 1: DATA
TI - Evaluation of LLM-Based Strategies for the Extraction of Food Product Information from Online Shops
SN - 978-989-758-758-0
AU - Brosch C.
AU - Brumm S.
AU - Krieger R.
AU - Scheffler J.
PY - 2025
SP - 709
EP - 715
DO - 10.5220/0013647300003967
PB - SciTePress