Saved in:
Bibliographic Details
Main Authors: Hongwimol, Pollawat, Shang, Haoning, Wang, Chutong, Wan, Zhichao, Gao, Yi, Li, Yuanming, Gui, Lin, Sun, Wenhao, Yu, Cheng
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2604.16950
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866918453209726976
author Hongwimol, Pollawat
Shang, Haoning
Wang, Chutong
Wan, Zhichao
Gao, Yi
Li, Yuanming
Gui, Lin
Sun, Wenhao
Yu, Cheng
author_facet Hongwimol, Pollawat
Shang, Haoning
Wang, Chutong
Wan, Zhichao
Gao, Yi
Li, Yuanming
Gui, Lin
Sun, Wenhao
Yu, Cheng
contents Product attribute extraction in e-commerce is bottlenecked by ontologies that are inconsistent, incomplete, and costly to maintain. We present AutoPKG, a multi-agent Large Language Model (LLM) framework that automatically constructs a Product-attribute Knowledge Graph (PKG) from multimodal product content. AutoPKG induces product types and type-specific attribute keys on demand, extracts attribute values from text and images, and consolidates updates through a centralized decision agent that maintains a globally consistent canonical graph. We also propose an evaluation protocol for dynamic PKGs that measures type and key validity, consolidation quality, and edge-level accuracy for value assertions after canonicalization. On a large real-world marketplace catalog dataset from Lazada (Alibaba), AutoPKG achieves up to 0.953 Weighted Knowledge Efficiency (WKE) for product types, 0.724 WKE for attribute keys, and 0.531 edge-level F1 for multimodal value extraction. Across three public benchmarks, our method improves edge-level exact-match F1 by 0.152 and yields a precision gain of 0.208 on the attribute extraction application. Online A/B tests show that AutoPKG-derived attributes increase Gross Merchandise Value (GMV) in Badge by 3.81 percent, in Search by 5.32 percent, and in Recommendation by 7.89 percent, supporting the practical value of AutoPKG in production.
format Preprint
id arxiv_https___arxiv_org_abs_2604_16950
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle AutoPKG: An Automated Framework for Dynamic E-commerce Product-Attribute Knowledge Graph Construction
Hongwimol, Pollawat
Shang, Haoning
Wang, Chutong
Wan, Zhichao
Gao, Yi
Li, Yuanming
Gui, Lin
Sun, Wenhao
Yu, Cheng
Artificial Intelligence
Product attribute extraction in e-commerce is bottlenecked by ontologies that are inconsistent, incomplete, and costly to maintain. We present AutoPKG, a multi-agent Large Language Model (LLM) framework that automatically constructs a Product-attribute Knowledge Graph (PKG) from multimodal product content. AutoPKG induces product types and type-specific attribute keys on demand, extracts attribute values from text and images, and consolidates updates through a centralized decision agent that maintains a globally consistent canonical graph. We also propose an evaluation protocol for dynamic PKGs that measures type and key validity, consolidation quality, and edge-level accuracy for value assertions after canonicalization. On a large real-world marketplace catalog dataset from Lazada (Alibaba), AutoPKG achieves up to 0.953 Weighted Knowledge Efficiency (WKE) for product types, 0.724 WKE for attribute keys, and 0.531 edge-level F1 for multimodal value extraction. Across three public benchmarks, our method improves edge-level exact-match F1 by 0.152 and yields a precision gain of 0.208 on the attribute extraction application. Online A/B tests show that AutoPKG-derived attributes increase Gross Merchandise Value (GMV) in Badge by 3.81 percent, in Search by 5.32 percent, and in Recommendation by 7.89 percent, supporting the practical value of AutoPKG in production.
title AutoPKG: An Automated Framework for Dynamic E-commerce Product-Attribute Knowledge Graph Construction
topic Artificial Intelligence
url https://arxiv.org/abs/2604.16950