用大模型从电商页面提取食品信息，间接方法更省成本
Evaluation of LLM-based Strategies for the Extraction of Food Product Information from Online Shops
- 通过生成函数间接提取，减少直接调用大模型次数
- 间接方法准确率96.48%，仅比直接方法低1.61%
- 调用次数减少95.82%，显著提升效率和降低成本
生成式AI与大语言模型（LLMs）在自动化提取网页结构化信息方面具有巨大潜力。本文聚焦电商平台的食品商品页，探索基于数据模式约束的提取方法，以获取成分列表、营养表等关键属性。我们在包含3,000个食品商品页的定制数据集上，对比了两种基于LLM的方法：直接提取与通过生成函数的间接提取。结果表明，尽管间接方法准确率略低（96.48%，较直接提取下降1.61%），但将所需LLM调用次数减少了95.82%，带来显著的效率提升与更低的运营成本。这表明，间接提取适用于基于模板的网页中大规模信息提取任务，具备可扩展性与成本优势。
原文摘要 · Abstract (English)
Generative AI and large language models (LLMs) offer significant potential for automating the extraction of structured information from web pages. In this work, we focus on food product pages from online retailers and explore schema-constrained extraction approaches to retrieve key product attributes, such as ingredient lists and nutrition tables. We compare two LLM-based approaches, direct extraction and indirect extraction via generated functions, evaluating them in terms of accuracy, efficiency, and cost on a curated dataset of 3,000 food product pages from three different online shops. Our results show that although the indirect approach achieves slightly lower accuracy (96.48\%, $-1.61\%$ compared to direct extraction), it reduces the number of required LLM calls by 95.82\%, leading to substantial efficiency gains and lower operational costs. These findings suggest that indirect extraction approaches can provide scalable and cost-effective solutions for large-scale information extraction tasks from template-based web pages using LLMs.
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。