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

arXiv: https://arxiv.org/abs/2506.21585 · HTML: https://mlsanity.com/paper/2506.21585/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 3 of its 5 references that are in the map.
- First posted on arXiv 17 Jun 2025.

## Builds on (most cited first, 3 of 3)

- [Retrieval-Augmented Code Generation for Universal Information Extraction](https://mlsanity.com/paper/2311.02962/) (2023)
- [KnowCoder: Coding Structured Knowledge into LLMs for Universal Information Extraction](https://mlsanity.com/paper/2403.07969/) (2024)
- [AutoScraper: A Progressive Understanding Web Agent for Web Scraper Generation](https://mlsanity.com/paper/2404.12753/) (2024)

## Abstract (arXiv)

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%, -1.61% 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.