EC-Guide: A Comprehensive E-Commerce Guide for Instruction Tuning and Quantization

TL;DR

EC-Guide is a comprehensive framework that enhances large language models for e-commerce tasks through instruction tuning, quantization, and Chain-of-Thought integration, achieving top placements in a major competition.

Contribution

It introduces a domain-specific guide for instruction tuning and quantization of LLMs tailored to e-commerce, with a model-agnostic approach and inference enhancements.

Findings

Achieved 2nd place in Amazon KDD Cup'24 Track 2

Achieved 5th place in Amazon KDD Cup'24 Track 5

Demonstrated effective scalability across larger systems

Abstract

Large language models (LLMs) have attracted considerable attention in various fields for their cost-effective solutions to diverse challenges, especially with advancements in instruction tuning and quantization. E-commerce, with its complex tasks and extensive product-user interactions, presents a promising application area for LLMs. However, the domain-specific concepts and knowledge inherent in e-commerce pose significant challenges for adapting general LLMs. To address this issue, we developed EC-Guide \href{https://github.com/fzp0424/EC-Guide-KDDUP-2024}, a comprehensive e-commerce guide for instruction tuning and quantization of LLMs. We also heuristically integrated Chain-of-Thought (CoT) during inference to enhance arithmetic performance. Our approach achieved the 2nd place in Track 2 and 5th place in Track 5 at the Amazon KDD Cup'24 \href{https://www.aicrowd.com/challenges/amazon-kdd-cup-2024-multi-task-online-shopping-challenge-for-llms}. Additionally, our solution is model-agnostic, enabling effective scalability across larger systems.