{"total":18,"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":"2304.09433","title":"Language Models Enable Simple Systems for Generating Structured Views of Heterogeneous Data Lakes","created":"2023-04-19","cited_by_count":111,"area":null},{"id":"2311.07989","title":"Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Code","created":"2023-11-14","cited_by_count":62,"area":null},{"id":"2308.03107","title":"Embedding-based Retrieval with LLM for Effective Agriculture Information Extracting from Unstructured Data","created":"2023-08-06","cited_by_count":16,"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":"2310.00749","title":"SEED: Domain-Specific Data Curation With Large Language Models","created":"2023-10-01","cited_by_count":10,"area":null},{"id":"2211.03256","title":"On Web-based Visual Corpus Construction for Visual Document Understanding","created":"2022-11-07","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":"2402.18262","title":"Hierarchical Multimodal Pre-training for Visually Rich Webpage Understanding","created":"2024-02-28","cited_by_count":4,"area":null},{"id":"2407.15502","title":"WebRPG: Automatic Web Rendering Parameters Generation for Visual Presentation","created":"2024-07-22","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":"2404.08860","title":"Enhancing Mobile \"How-to\" Queries with Automated Search Results Verification and Reranking","created":"2024-04-13","cited_by_count":3,"area":null},{"id":"2402.14129","title":"Combining Language and Graph Models for Semi-structured Information Extraction on the Web","created":"2024-02-21","cited_by_count":1,"area":null},{"id":"2502.02167","title":"Multilingual Attribute Extraction from News Web Pages","created":"2025-02-04","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":"2310.16303","title":"URL-BERT: Training Webpage Representations via Social Media Engagements","created":"2023-10-25","cited_by_count":0,"area":null},{"id":"2604.04353","title":"ReFinE: Streamlining UI Mockup Iteration with Research Findings","created":"2026-04-06","cited_by_count":0,"area":null},{"id":"2607.21284","title":"news-crawler-LM: A Small Long-Context Model For High-Quality News Crawling","created":"2026-07-23","cited_by_count":0,"area":null}],"next_cursor":null}