Unlike professional Business-to-Consumer (B2C) e-commerce platforms (e.g., Amazon), Consumer-to-Consumer (C2C) platforms (e.g., Facebook marketplace) are mainly targeting individual sellers who usually lack sufficient experience in e-commerce. Individual sellers often struggle to compose proper descriptions for selling products. With the recent advancement of Multimodal Large Language Models (MLLMs), we attempt to integrate such state-of-the-art generative AI technologies into the product listing process. To this end, we develop IPL, an Intelligent Product Listing tool tailored to generate descriptions using various product attributes such as category, brand, color, condition, etc. IPL enables users to compose product descriptions by merely uploading photos of the selling product. More importantly, it can imitate the content style of our C2C platform Xianyu. This is achieved by employing domain-specific instruction tuning on MLLMs and adopting the multi-modal Retrieval-Augmented Generation (RAG) process. A comprehensive empirical evaluation demonstrates that the underlying model of IPL significantly outperforms the base model in domain-specific tasks while producing less hallucination. IPL has been successfully deployed in our production system, where 72% of users have their published product listings based on the generated content, and those product listings are shown to have a quality score 5.6% higher than those without AI assistance.

翻译：与专业的B2C电商平台（如亚马逊）不同，C2C平台（如Facebook marketplace）主要面向通常缺乏电商经验的个人卖家。个人卖家往往难以撰写合适的商品描述。随着多模态大语言模型（MLLMs）的最新进展，我们尝试将此类前沿生成式AI技术整合到商品发布流程中。为此，我们开发了IPL——一款专为利用商品类别、品牌、颜色、状态等多种属性生成描述而设计的智能商品发布工具。用户仅需上传待售商品的照片，IPL即可协助撰写商品描述。更重要的是，它能够模仿我们C2C平台闲鱼的内容风格。这是通过对MLLMs进行领域特定的指令微调，并采用多模态检索增强生成（RAG）流程实现的。全面的实证评估表明，IPL的基础模型在领域特定任务中显著优于原始基础模型，同时产生的幻觉内容更少。IPL已成功部署于我们的生产系统，其中72%的用户基于生成内容发布商品，且这些商品列表的质量评分比未使用AI辅助的商品高出5.6%。