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 2501.01237cs.CL
收藏

基于大语言模型的产品属性值抽取的自优化策略

Self-Refinement Strategies for LLM-based Product Attribute Value Extraction

University of Mannheim(曼海姆大学)

Alexander Brinkmann, Christian Bizer

AI总结:

本文研究两种自优化技术(基于错误的提示重写和自校正)在基于大语言模型的产品属性值抽取任务中的应用,发现其未提升性能却增加成本,而微调在有开发数据时性能最优且启动成本随数据量增加被抵消。

摘要:

属性值对形式的结构化产品数据对于电商平台支持分面产品搜索、基于属性的产品比较等功能至关重要。然而,卖家常提供非结构化产品描述,因此需要进行属性值抽取以确保数据一致性和可用性。大语言模型(LLMs)在少样本场景下已展现出产品属性值抽取的潜力。近期研究表明,自优化技术可提升LLMs在代码生成、文本转SQL翻译等任务中的性能;但在其他任务中,应用这些技术因处理额外token导致成本增加,却未提升性能。本文研究将两种自优化技术(基于错误的提示重写和自校正)应用于产品属性值抽取任务,使用GPT-4o在零样本、少样本上下文学习和微调场景中评估这些技术。实验显示,两种自优化技术均未显著提升抽取性能,却大幅增加了处理成本;在有开发数据的场景中,微调性能最高,且随着产品描述数量增加,微调的启动成本被抵消。

英文摘要:

Structured product data, in the form of attribute-value pairs, is essential for e-commerce platforms to support features such as faceted product search and attribute-based product comparison. However, vendors often provide unstructured product descriptions, making attribute value extraction necessary to ensure data consistency and usability. Large language models (LLMs) have demonstrated their potential for product attribute value extraction in few-shot scenarios. Recent research has shown that self-refinement techniques can improve the performance of LLMs on tasks such as code generation and text-to-SQL translation. For other tasks, the application of these techniques has resulted in increased costs due to processing additional tokens, without achieving any improvement in performance. This paper investigates applying two self-refinement techniques (error-based prompt rewriting and self-correction) to the product attribute value extraction task. The self-refinement techniques are evaluated across zero-shot, few-shot in-context learning, and fine-tuning scenarios using GPT-4o. The experiments show that both self-refinement techniques fail to significantly improve the extraction performance while substantially increasing processing costs. For scenarios with development data, fine-tuning yields the highest performance, while the ramp-up costs of fine-tuning are balanced out as the amount of product descriptions increases.

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。

↑