用大模型零样本识别商品属性，效果更好且省数据。
Exploring Large Language Models for Product Attribute Value Identification
- 分两步提示法+上下文学习，零样本下更准
- 指令微调后在有数据时性能进一步提升
- 适合缺乏标注数据的电商场景
商品属性值识别（PAVI）旨在从商品信息中自动提取属性及其取值，支持商品搜索、推荐和比价等功能。现有方法多依赖BART、T5等预训练模型的微调，需大量任务特定数据，且难以泛化到新属性。本文探索使用LLaMA、Mistral等大语言模型作为更高效、更鲁棒的替代方案。提出多种策略：对比零样本下的单步与双步提示方法，利用参数化与非参数化知识进行上下文学习；引入基于预训练T5的密集演示检索器，并对LLM进行任务指令微调。在两个商品基准数据集上的大量实验表明，双步提示法在零样本设置下显著提升性能，指令微调在有训练数据时进一步增强效果，验证了使用LLMs进行PAVI的实际优势。
原文摘要 · Abstract (English)
Product attribute value identification (PAVI) involves automatically identifying attributes and their values from product information, enabling features like product search, recommendation, and comparison. Existing methods primarily rely on fine-tuning pre-trained language models, such as BART and T5, which require extensive task-specific training data and struggle to generalize to new attributes. This paper explores large language models (LLMs), such as LLaMA and Mistral, as data-efficient and robust alternatives for PAVI. We propose various strategies: comparing one-step and two-step prompt-based approaches in zero-shot settings and utilizing parametric and non-parametric knowledge through in-context learning examples. We also introduce a dense demonstration retriever based on a pre-trained T5 model and perform instruction fine-tuning to explicitly train LLMs on task-specific instructions. Extensive experiments on two product benchmarks show that our two-step approach significantly improves performance in zero-shot settings, and instruction fine-tuning further boosts performance when using training data, demonstrating the practical benefits of using LLMs for PAVI.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。