{"total":25,"rows":[{"id":"2210.03347","title":"Pix2Struct: Screenshot Parsing as Pretraining for Visual Language Understanding","created":"2022-10-07","cited_by_count":366,"area":null},{"id":"2307.12856","title":"A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis","created":"2023-07-24","cited_by_count":353,"area":null},{"id":"2402.05930","title":"WebLINX: Real-World Website Navigation with Multi-Turn Dialogue","created":"2024-02-08","cited_by_count":180,"area":null},{"id":"2305.11854","title":"Multimodal Web Navigation with Instruction-Finetuned Foundation Models","created":"2023-05-19","cited_by_count":160,"area":null},{"id":"2503.01151","title":"ReaderLM-v2: Small Language Model for HTML to Markdown and JSON","created":"2025-03-03","cited_by_count":15,"area":null},{"id":"2210.02849","title":"XDoc: Unified Pre-training for Cross-Format Document Understanding","created":"2022-10-06","cited_by_count":12,"area":null},{"id":"2305.14898","title":"PIVOINE: Instruction Tuning for Open-world Information Extraction","created":"2023-05-24","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":"2203.02656","title":"Deep Partial Multiplex Network Embedding","created":"2022-03-05","cited_by_count":5,"area":null},{"id":"2402.14652","title":"Cleaner Pretraining Corpus Curation with Neural Web Scraping","created":"2024-02-22","cited_by_count":5,"area":null},{"id":"2602.12187","title":"SAGEO Arena: A Realistic Environment for Evaluating Search-Augmented Generative Engine Optimization","created":"2026-02-12","cited_by_count":5,"area":null},{"id":"2211.05284","title":"FormLM: Recommending Creation Ideas for Online Forms by Modelling Semantic and Structural Information","created":"2022-11-10","cited_by_count":3,"area":null},{"id":"2210.12445","title":"Cross-domain Generalization for AMR Parsing","created":"2022-10-22","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":"2506.21096","title":"DALR: Dual-level Alignment Learning for Multimodal Sentence Representation Learning","created":"2025-06-26","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":"2312.08274","title":"High-throughput Biomedical Relation Extraction for Semi-Structured Web Articles Empowered by Large Language Models","created":"2023-12-13","cited_by_count":1,"area":null},{"id":"2403.01698","title":"Hypertext Entity Extraction in Webpage","created":"2024-03-04","cited_by_count":1,"area":null},{"id":"2509.25107","title":"Knowledge Extraction on Semi-Structured Content: Does It Remain Relevant for Question Answering in the Era of LLMs?","created":"2025-09-29","cited_by_count":1,"area":null},{"id":"2403.16915","title":"Coarse-Tuning for Ad-hoc Document Retrieval Using Pre-trained Language Models","created":"2024-03-25","cited_by_count":0,"area":null},{"id":"2411.08278","title":"Knowledge Bases in Support of Large Language Models for Processing Web News","created":"2024-11-13","cited_by_count":0,"area":null},{"id":"2601.05502","title":"Evaluating the Use of LLMs for Automated DOM-Level Resolution of Web Performance Issues","created":"2026-01-09","cited_by_count":0,"area":null},{"id":"2603.13773","title":"LiveWeb-IE: A Benchmark For Online Web Information Extraction","created":"2026-03-14","cited_by_count":0,"area":null},{"id":"2603.29161","title":"Webscraper: Leverage Multimodal Large Language Models for Index-Content Web Scraping","created":"2026-03-31","cited_by_count":0,"area":null},{"id":"2606.14821","title":"Co-Scraper: query-aware DOM Pruning and Reusable Scraper Synthesis for Lightweight Web Data Extraction","created":"2026-06-12","cited_by_count":0,"area":null}],"next_cursor":null}