Welcome to the Large Language Model for E-Commerce Workshop at WWW’25.
Call for Papers
Large Language Models (LLMs) have recently emerged as transformative tools in artificial intelligence, revolutionizing various domains. In e-commerce, LLMs have demonstrated remarkable potential to drive innovation and enhance customer experiences. E-commerce data typically includes multi-modal information, such as product titles, images, user-item interactions, and customer reviews. The richness and diversity of this data create unique opportunities for designing and applying advanced LLM models. LLMs have already been applied to a range of e-commerce tasks, including product recommendation, search, classification, question answering, and advertising. They have also been integrated into real-world production systems, such as Amazon Rufus and Taobao Wenwen. Despite these successes, the adoption of LLMs in e-commerce is still in its early stages. Significant challenges remain, such as ensuring the accuracy of LLM-generated content, improving efficiency, mitigating biases, and safeguarding user privacy and data security.
This workshop seeks to explore a wide range of topics related to the use of LLMs in e-commerce, encompassing methods, datasets, applications, and systems. We invite submissions that address these challenges and contribute to advancing the state-of-the-art in LLMs for e-commerce.
Important Dates
- Submission Deadline: January 26, 2025
- Notification: February 28, 2025
- Camera-ready: March 03, 2025
- Workshop: April 28 or 29, 2025
All submission deadlines are end-of-day in the Anywhere on Earth (AoE) time zone.
Fast-Track
We accept the Fast-Track of WWW 2025. Please follow the instruction in https://www2025.thewebconf.org/workshop-fast-track.
Submission
Please submit your work through https://openreview.net/group?id=ACM.org/TheWebConf/2025/Workshop/LLM4ECommerce
Submissions of papers must be in English, in PDF format, in the current ACM two-column conference format. Suitable LaTeX, Word, and Overleaf templates are available from the ACM Website (use the “sigconf” proceedings template for LaTeX and the Interim Template for Word) (also available in Overleaf). The recommended setting for LaTeX is: \documentclass[sigconf, anonymous, review]{acmart}.
- Long paper: Submission of original work up to eight pages in length (unlimited references and appendix).
- Short paper: Submission of work in progress with preliminary results, and position papers, up to four pages in length (unlimited references and appendix).
Topics
Foundations
- Pre-training LLMs on E-Commerce data
- Prompting LLMs for E-Commerce
- Alignment Tuning for E-Commerce
- Agent Systems for E-Commerce
Applications
- Product Search and Recommendation
- Product Information Generation, including Review Summary
- Product Question Answering
- Personalized Recommendation
- Advertising
- Business Analytics
- E-Commerce datasets
- Customer Behavior Analysis
- Fairness and bias in E-Commerce
- Benchmarks and Evaluation for E-Commerce tasks
System
- Scalable and Distributed Training
- Model Serving and Deployment
- Machine Learning Systems for E-Commerce LLM