用轻量模型高效提取网页结构化数据，精度超主流大模型。
AXE: Low-Cost Cross-Domain Web Structured Information Extraction
- 将网页树状结构视为可修剪的枝干，剔除无关节点
- 0.6B小模型在SWDE上达88.1% F1，零样本超越更大模型
- 通过物理节点追踪确保输出可验证，适合低资源场景
从网页中提取结构化数据常面临手工规则脆弱与大语言模型成本高昂之间的权衡。我们提出AXE（自适应X-Path提取器），将HTML DOM视为需修剪的树结构，而非单纯文本墙。AXE采用专用“修剪”机制剥离冗余节点，保留高密度上下文，使仅0.6B规模的轻量语言模型也能生成精准结构化输出。为确保模型可靠性，引入基于物理位置的XPath解析（GXR），保证每项提取结果均可追溯至原始节点。尽管模型规模极小，AXE在零样本条件下实现88.1% F1得分，超越多个更大、全训练的替代方案，在SWDE数据集上表现领先。我们开源了专用适配器，旨在为大规模网络信息抽取提供实用且低成本路径。代码与适配器已公开于 https://github.com/abdo-Mansour/axetract。
原文摘要 · Abstract (English)
Extracting structured data from the web is often a trade-off between the brittle nature of manual heuristics and the prohibitive cost of Large Language Models. We introduce AXE (Adaptive X-Path Extractor), a pipeline that rethinks this process by treating the HTML DOM as a tree that needs pruning rather than just a wall of text to be read. AXE uses a specialized "pruning" mechanism to strip away boilerplate and irrelevant nodes, leaving behind a distilled, high-density context that allows a tiny 0.6B LLM to generate precise, structured outputs. To keep the model honest, we implement Grounded XPath Resolution (GXR), ensuring every extraction is physically traceable to a source node. Despite its low footprint, AXE achieves state-of-the-art zero-shot performance, outperforming several much larger, fully-trained alternatives with an F1 score of 88.1% on the SWDE dataset. By releasing our specialized adaptors, we aim to provide a practical, cost-effective path for large-scale web information extraction. Our code and adaptors are publicly available at https://github.com/abdo-Mansour/axetract.
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。