EcomGPT：面向电子商务的采用任务链任务进行指令微调的大语言模型
EcomGPT: Instruction-tuning Large Language Models with Chain-of-Task Tasks for E-commerce
AI总结：
针对通用大语言模型在电商场景泛化能力不足的问题，构建含250万条数据的电商指令数据集EcomInstruct，基于任务链任务训练出EcomGPT，其电商跨任务泛化表现优于ChatGPT。
摘要：
近年来，以ChatGPT为代表的遵循指令的大语言模型（LLM）在通用自然语言处理（NLP）任务中表现出优异性能。然而，电子商务数据的独特特性给通用LLM带来了巨大挑战，迫切需要一款专门针对电商场景、具备强大跨数据集/任务泛化能力的LLM。为解决该问题，本研究提出了首个电商指令数据集EcomInstruct，总计包含250万条指令数据。EcomInstruct通过利用商品信息、用户评论等电商基础数据类型构建原子任务（即解决最终任务时隐含涉及的中间任务，我们也称之为任务链任务），扩大了数据规模与任务多样性。我们以BLOOMZ为骨干模型，用EcomInstruct训练得到不同参数规模的EcomGPT。得益于从任务链任务中习得的基础语义理解能力，EcomGPT展现出优异的零样本泛化能力。大量实验与人工评估表明，在电商任务的跨数据集/任务泛化方面，EcomGPT的表现优于ChatGPT。
英文摘要：
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.
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。
