Using Brand Knowledge Bases and LLM Agents to Enhance E-commerce Retailers' Catalog Quality

ACM International Conference on Web Search and Data Mining (WSDM) 2026 Open access

Read full text
Authors: Hayreddin Çeker, Gang Luo, Kee Kiat Koo, Prashant Mathur, Wencong You, Atharva Amdekar, Rob Barton, K L Navaneet, Vidit Bansal, Karim Bouyarmane
DOI: 10.1145/3773966.3784969
Cited by: 0
References: 1

Abstract

For e-commerce retailers, high-quality product catalogs are vital to customer experience. Yet, despite lots of data cleaning efforts, catalog quality, especially in large catalogs, remains suboptimal. This paper shows how to use unstructured brand knowledge base data as a reference and a large language model agent to automatically enhance an e-commerce retailer's catalog quality. Unlike prior methods that usually repair and match product entries separately, our method does both concurrently. Our evaluation results show its effectiveness.

Fields of Study & Subjects

Data Quality and Management Library Science and Information Systems Semantic Web and Ontologies

Publication details

Journal / source
ACM International Conference on Web Search and Data Mining (WSDM)
Pages
1343–1344
Publication date
16 February 2026
Language
EN