EcomGPT: Instruction-tuning Large Language Models with Chain-of-Task Tasks for E-commerce
Li, Yangning, Ma, Shirong, Wang, Xiaobin, Huang, Shen, Jiang, Chengyue, Zheng, Hai-Tao, Xie, Pengjun, Huang, Fei, Jiang, Yong
–arXiv.org Artificial Intelligence
Recently, instruction-following Large Language Models (LLMs) , represented by ChatGPT, have exhibited exceptional performance in general Natural Language Processing (NLP) tasks. However, the unique characteristics of E-commerce data pose significant challenges to general LLMs. An LLM tailored specifically for E-commerce scenarios, possessing robust cross-dataset/task generalization capabilities, is a pressing necessity. To solve this issue, in this work, we proposed the first e-commerce instruction dataset EcomInstruct, with a total of 2.5 million instruction data. EcomInstruct scales up the data size and task diversity by constructing atomic tasks with E-commerce basic data types, such as product information, user reviews. Atomic tasks are defined as intermediate tasks implicitly involved in solving a final task, which we also call Chain-of-Task tasks. We developed EcomGPT with different parameter scales by training the backbone model BLOOMZ with the EcomInstruct. Benefiting from the fundamental semantic understanding capabilities acquired from the Chain-of-Task tasks, EcomGPT exhibits excellent zero-shot generalization capabilities. Extensive experiments and human evaluations demonstrate that EcomGPT outperforms ChatGPT in term of cross-dataset/task generalization on E-commerce tasks.
arXiv.org Artificial Intelligence
Aug-28-2023
- Country:
- Europe (0.28)
- North America > United States
- Minnesota (0.14)
- Genre:
- Research Report > New Finding (1.00)
- Industry:
- Information Technology > Services > e-Commerce Services (1.00)
- Technology: