PUMGPT: Leveraging AI for Advanced Product Management in E-Commerce
- DOI
- 10.2991/978-94-6463-787-8_15How to use a DOI?
- Keywords
- Large Vision-Language Models (LVLMs); E-commerce; Product Understanding; AI in Retail; Hallucination Detection; Attribute Inference; Category Prediction; Caption Generation; PUMBENCH; Product Management
- Abstract
Product management in e-commerce relies on accurate understanding of product attributes, categories, and presentations to enhance user experiences and streamline workflows. This paper introduces PUMGPT, a specialized large vision-language model (LVLM) designed to address challenges in product understanding tasks across multi-modal data. PUMGPT employs a robust data curation pipeline, including a novel hallucination detection framework, to filter noisy product data from over one million samples, resulting in a high-quality training dataset of 663k entries. The model is evaluated on PUMBENCH, a benchmark suite that tests capabilities across five critical product management tasks, such as caption generation, attribute inference, and category prediction. Experimental results demonstrate that PUMGPT outperforms existing LVLMs, including GPT-4V, showcasing its superior ability to integrate domain-specific insights with advanced AI methods. This work highlights the transformative potential of AI in e-commerce product management, offering scalable solutions for improving operational efficiency and customer engagement.
- Copyright
- © 2025 The Author(s)
- Open Access
- Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.
Cite this article
TY - CONF AU - Muhammed Abeed Nabith PY - 2025 DA - 2025/07/17 TI - PUMGPT: Leveraging AI for Advanced Product Management in E-Commerce BT - Proceedings of the Recent Advances in Artificial Intelligence for Sustainable Development (RAISD 2025) PB - Atlantis Press SP - 162 EP - 176 SN - 1951-6851 UR - https://doi.org/10.2991/978-94-6463-787-8_15 DO - 10.2991/978-94-6463-787-8_15 ID - Nabith2025 ER -