arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2408.02006cs.CL
收藏

LLaSA:大型语言与电子商务购物助手

LLaSA: Large Language and E-Commerce Shopping Assistant

Zhejiang University(浙江大学);Peking University(北京大学);Harbin Institute of Technology (Shenzhen)(哈尔滨工业大学(深圳));The Hong Kong University of Science and Technology (Guangzhou)(香港科技大学(广州))

Shuo Zhang, Boci Peng, Xinping Zhao, Boren Hu, Yun Zhu, Yanjia Zeng, Xuming Hu

AI总结:

本文提出 LLaSA,基于 LLM 和含 65,000 样本的 EshopInstruct 指令微调构建通用电商购物助手,并通过推理优化在 ShopBench 获总排名第 3。

摘要:

电子商务平台因其广泛普及和便利性而迅速发展。为客户开发一款电子商务购物助手,对于帮助他们快速找到心仪产品并精准推荐其所需商品至关重要。然而,以往大多数购物助手面临两个主要问题:(1)任务专用性,这需要为不同任务开发不同模型,从而增加开发成本并限制效果;(2)泛化能力差,即训练后的模型在最新产品上表现不足。为解决这些问题,我们利用大型语言模型(LLM)构建一款全能助手,借助其处理多种任务的娴熟能力和优越的泛化能力。尽管如此,LLM 缺乏关于电子商务概念的内在知识。为解决这一点,我们创建了一个包含 65,000 个样本和多种任务的指令数据集,称为 EshopInstruct。通过在该数据集上进行指令微调,名为 LLaSA 的助手展现出作为全能助手运行的潜力。此外,我们提出多种推理优化策略,以在有限推理资源下提升性能。在 Amazon KDD Cup 2024 Challenge 中,我们提出的方法 LLaSA 在包含 57 项任务和约 20,000 个问题的 ShopBench 上获得总排名第 3 名,并且我们在每个赛道都取得前 5 名,尤其在 track4 中,我们在所有学生团队中取得最佳性能结果。我们的广泛实践充分证明,LLM 具备成为胜任的电子商务购物助手的巨大潜力。

英文摘要:

The e-commerce platform has evolved rapidly due to its widespread popularity and convenience. Developing an e-commerce shopping assistant for customers is crucial to aiding them in quickly finding desired products and recommending precisely what they need. However, most previous shopping assistants face two main problems: (1) task-specificity, which necessitates the development of different models for various tasks, thereby increasing development costs and limiting effectiveness; and (2) poor generalization, where the trained model performs inadequately on up-to-date products. To resolve these issues, we employ Large Language Models (LLMs) to construct an omnipotent assistant, leveraging their adeptness at handling multiple tasks and their superior generalization capability. Nonetheless, LLMs lack inherent knowledge of e-commerce concepts. To address this, we create an instruction dataset comprising 65,000 samples and diverse tasks, termed as EshopInstruct. Through instruction tuning on our dataset, the assistant, named LLaSA, demonstrates the potential to function as an omnipotent assistant. Additionally, we propose various inference optimization strategies to enhance performance with limited inference resources. In the Amazon KDD Cup 2024 Challenge, our proposed method, LLaSA, achieved an overall ranking of 3rd place on ShopBench, including 57 tasks and approximately 20,000 questions, and we secured top-5 rankings in each track, especially in track4, where we achieved the best performance result among all student teams. Our extensive practices fully demonstrate that LLMs possess the great potential to be competent e-commerce shopping assistants.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑