LLaMA-E: Empowering E-commerce Authoring with Object-Interleaved Instruction Following

TL;DR

LLaMA-E is a specialized large language model designed for e-commerce content creation, effectively understanding and utilizing object features to improve diverse authoring tasks and outperform existing models.

Contribution

The paper introduces LLaMA-E, the first LLM tailored for e-commerce authoring that integrates object features for comprehensive scenario understanding.

Findings

Achieves state-of-the-art performance on e-commerce tasks.

Excels in zero-shot practical applications.

Effectively models object interleaved instruction following.

Abstract

E-commerce authoring entails creating engaging, diverse, and targeted content to enhance preference elicitation and retrieval experience. While Large Language Models (LLMs) have revolutionized content generation, they often fall short in e-commerce applications due to their limited memorization of domain-specific features. This paper proposes LLaMA-E, the unified e-commerce authoring models that address the contextual preferences of customers, sellers, and platforms, the essential objects in e-commerce operation. We design the instruction set derived from tasks of ads generation, query-enhanced product title rewriting, product classification, purchase intent speculation, and general e-commerce Q&A. The instruction formulation ensures the interleaved cover of the presented and required object features, allowing the alignment of base models to parameterise e-commerce knowledge comprehensively. The proposed LLaMA-E models achieve state-of-the-art evaluation performance and exhibit the advantage in zero-shot practical applications. To our knowledge, this is the first LLM tailored to empower authoring applications with comprehensive scenario understanding by integrating features focused on participated objects.