{"total":13,"rows":[{"id":"2412.11919","title":"RetroLLM: Empowering Large Language Models to Retrieve Fine-grained Evidence within Generation","created":"2024-12-16","cited_by_count":20,"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":"2512.09483","title":"Source Coverage and Citation Bias in LLM-based vs. Traditional Search Engines","created":"2025-12-10","cited_by_count":6,"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":"2411.07441","title":"Automatically Detecting Online Deceptive Patterns","created":"2024-11-11","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":"2602.01838","title":"AXE: Low-Cost Cross-Domain Web Structured Information Extraction","created":"2026-02-02","cited_by_count":1,"area":null},{"id":"2508.20778","title":"SEAL: Structure and Element Aware Learning to Improve Long Structured Document Retrieval","created":"2025-08-28","cited_by_count":0,"area":null},{"id":"2602.15189","title":"ScrapeGraphAI-100k: Dataset for Schema-Constrained LLM Generation","created":"2026-02-16","cited_by_count":0,"area":null},{"id":"2605.08305","title":"LLMSYS-HPOBench: Hyperparameter Optimization Benchmark Suite for Real-World LLM Systems","created":"2026-05-08","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},{"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},{"id":"2609.06993","title":"LatentMD: Benchmarking Markdown Boundary Failures in LLM-Generated Text","created":"2026-09-07","cited_by_count":0,"area":null}],"next_cursor":null}