Result Details

GNN-Based Token Reduction for LLM Semantic Element Detection in E-Commerce Product Pages

SALEM, H.; BURGET, R. GNN-Based Token Reduction for LLM Semantic Element Detection in E-Commerce Product Pages. In Lecture Notes in Computer Science. Lecture Notes in Computer Science. Lyon: Springer Science and Business Media Deutschland GmbH, 2026. iss. 16625 LNCS, p. 311-314. ISBN: 9783032293718.
Type
conference paper
Language
English
Authors
Abstract

Applying Large Language Models (LLMs) to whole-page semantic element detection in e-commerce is prohibitively expensive: typical product pages contain hundreds to thousands of DOM elements, and LLM costs scale linearly with input tokens. We propose a hybrid approach that uses a Graph Neural Network (GraphSAGE) as a pre-filter to reduce the candidate set before LLM processing. Our preliminary results on the Klarna Product Page Dataset show approximately 90% reduction in elements sent to the LLM (from hundreds to 5–10 per page) while maintaining 94.5% nomination accuracy. This position paper presents the core idea, motivates the token-saving focus, and reports preliminary results to solicit feedback before thorough experimental evaluation in an extended journal submission.

Keywords

E-Commerce | Graph Neural Networks | Large Language Models | Semantic Element Detection | Token Reduction | Web Automation

URL
Published
2026
Pages
311–314
Journal
Lecture Notes in Computer Science, no. 16625 LNCS, ISSN
Proceedings
Lecture Notes in Computer Science
Conference
26th International Conference on Web Engineering
ISBN
9783032293718
Publisher
Springer Science and Business Media Deutschland GmbH
Place
Lyon
DOI
EID Scopus
BibTeX
@inproceedings{BUT212245,
  author="{} and Hamza {Salem} and Radek {Burget}",
  title="GNN-Based Token Reduction for LLM Semantic Element Detection in E-Commerce Product Pages",
  booktitle="Lecture Notes in Computer Science",
  year="2026",
  journal="Lecture Notes in Computer Science",
  number="16625 LNCS",
  pages="311--314",
  publisher="Springer Science and Business Media Deutschland GmbH",
  address="Lyon",
  doi="10.1007/978-3-032-29372-5\{_}31",
  isbn="9783032293718",
  url="https://link.springer.com/chapter/10.1007/978-3-032-29372-5_31"
}
Projects
Aplikace pokročilých technik pro kybernetickou bezpečnost a efektivní zpracování heterogenních dat., BUT, Vnitřní projekty VUT, FIT-S-26-9019, start: 2026-03-01, end: 2027-02-28, running
Departments
Back to top