{"total":14,"rows":[{"id":"2402.05930","title":"WebLINX: Real-World Website Navigation with Multi-Turn Dialogue","created":"2024-02-08","cited_by_count":180,"area":null},{"id":"2110.08518","title":"MarkupLM: Pre-training of Text and Markup Language for Visually-rich Document Understanding","created":"2021-10-16","cited_by_count":45,"area":null},{"id":"2202.00217","title":"WebFormer: The Web-page Transformer for Structure Information Extraction","created":"2022-02-01","cited_by_count":34,"area":null},{"id":"2201.10608","title":"DOM-LM: Learning Generalizable Representations for HTML Documents","created":"2022-01-25","cited_by_count":24,"area":null},{"id":"2310.00749","title":"SEED: Domain-Specific Data Curation With Large Language Models","created":"2023-10-01","cited_by_count":10,"area":null},{"id":"2511.23119","title":"Dripper: Token-Efficient Main HTML Extraction with a Lightweight LM","created":"2025-11-28","cited_by_count":8,"area":null},{"id":"2110.12320","title":"CoVA: Context-aware Visual Attention for Webpage Information Extraction","created":"2021-10-24","cited_by_count":6,"area":null},{"id":"2402.18262","title":"Hierarchical Multimodal Pre-training for Visually Rich Webpage Understanding","created":"2024-02-28","cited_by_count":4,"area":null},{"id":"2205.12386","title":"PLAtE: A Large-scale Dataset for List Page Web Extraction","created":"2022-05-24","cited_by_count":3,"area":null},{"id":"2111.02168","title":"The Klarna Product Page Dataset: Web Element Nomination with Graph Neural Networks and Large Language Models","created":"2021-11-03","cited_by_count":2,"area":null},{"id":"2502.15688","title":"XPath Agent: An Efficient XPath Programming Agent Based on LLM for Web Crawler","created":"2024-12-17","cited_by_count":2,"area":null},{"id":"2305.13805","title":"Towards Zero-shot Relation Extraction in Web Mining: A Multimodal Approach with Relative XML Path","created":"2023-05-23","cited_by_count":1,"area":null},{"id":"2408.04673","title":"AutoFAIR : Automatic Data FAIRification via Machine Reading","created":"2024-08-07","cited_by_count":0,"area":null},{"id":"2508.01096","title":"Cross-Domain Web Information Extraction at Pinterest","created":"2025-08-01","cited_by_count":0,"area":null}],"next_cursor":null}