Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.01838 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911555130490880 |
|---|---|
| author | Mansour, Abdelrahman Alshaer, Khaled W. Elsaban, Moataz |
| author_facet | Mansour, Abdelrahman Alshaer, Khaled W. Elsaban, Moataz |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_01838 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AXE: Low-Cost Cross-Domain Web Structured Information Extraction Mansour, Abdelrahman Alshaer, Khaled W. Elsaban, Moataz Computation and Language 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. |
| title | AXE: Low-Cost Cross-Domain Web Structured Information Extraction |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2602.01838 |