{"total":27,"rows":[{"id":"2412.07626","title":"OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations","created":"2024-12-10","cited_by_count":150,"area":"rag"},{"id":"2410.21169","title":"Document Parsing Unveiled: Techniques, Challenges, and Prospects for Structured Information Extraction","created":"2024-10-28","cited_by_count":44,"area":"rag"},{"id":"2412.02592","title":"OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation","created":"2024-12-03","cited_by_count":26,"area":"rag"},{"id":"2510.12323","title":"RAG-Anything: All-in-One RAG Framework","created":"2025-10-14","cited_by_count":20,"area":"rag"},{"id":"2512.03413","title":"BookRAG: A Hierarchical Structure-aware Index-based Approach for Retrieval-Augmented Generation on Complex Documents","created":"2025-12-03","cited_by_count":16,"area":"rag"},{"id":"2502.04176","title":"MRAMG-Bench: A Comprehensive Benchmark for Advancing Multimodal Retrieval-Augmented Multimodal Generation","created":"2025-02-06","cited_by_count":15,"area":"rag"},{"id":"2511.10390","title":"MonkeyOCR v1.5 Technical Report: Unlocking Robust Document Parsing for Complex Patterns","created":"2025-11-13","cited_by_count":13,"area":"rag"},{"id":"2512.20626","title":"MegaRAG: Multimodal Knowledge Graph-Based Retrieval Augmented Generation","created":"2025-11-26","cited_by_count":7,"area":"rag"},{"id":"2508.01680","title":"T-GRAG: A Dynamic GraphRAG Framework for Resolving Temporal Conflicts and Redundancy in Knowledge Retrieval","created":"2025-08-03","cited_by_count":6,"area":"rag"},{"id":"2602.24134","title":"AgenticOCR: Parsing Only What You Need for Efficient Retrieval-Augmented Generation","created":"2026-02-27","cited_by_count":5,"area":"rag"},{"id":"2602.10271","title":"MLDocRAG: Multimodal Long-Context Document Retrieval Augmented Generation","created":"2026-02-10","cited_by_count":4,"area":"rag"},{"id":"2509.21336","title":"HetaRAG: Hybrid Deep Retrieval-Augmented Generation across Heterogeneous Data Stores","created":"2025-09-12","cited_by_count":3,"area":"rag"},{"id":"2510.10828","title":"VeritasFi: An Adaptable, Multi-tiered RAG Framework for Multi-modal Financial Question Answering","created":"2025-10-12","cited_by_count":3,"area":"rag"},{"id":"2607.12764","title":"EvoGraph-R1: Self-Evolving Multimodal Knowledge Hypergraphs for Agentic Retrieval","created":"2026-07-14","cited_by_count":2,"area":"rag"},{"id":"2504.10258","title":"XY-Cut++: Advanced Layout Ordering via Hierarchical Mask Mechanism on a Novel Benchmark","created":"2025-04-14","cited_by_count":1,"area":"rag"},{"id":"2505.02418","title":"SymbioticRAG: Enhancing Document Intelligence Through Human-LLM Symbiotic Collaboration","created":"2025-05-05","cited_by_count":1,"area":"rag"},{"id":"2601.22055","title":"$G^2$-Reader: Dual Evolving Graphs for Multimodal Document QA","created":"2026-01-29","cited_by_count":1,"area":"rag"},{"id":"2604.04948","title":"From PDF to RAG-Ready: Evaluating Document Conversion Frameworks for Domain-Specific Question Answering","created":"2026-03-30","cited_by_count":1,"area":"rag"},{"id":"2606.07235","title":"FLOWREADER: Min-Cost Flow Optimization for Multi-Modal Long Document Q&A","created":"2026-06-05","cited_by_count":1,"area":"rag"},{"id":"2607.24861","title":"HVM-GraphRAG: Holistic-View Multimodal Graph Retrieval-Augmented Generation on Complex Document","created":"2026-07-26","cited_by_count":1,"area":"rag"},{"id":"2510.18339","title":"ECG-LLM -- training and evaluation of domain-specific large language models for electrocardiography","created":"2025-10-21","cited_by_count":0,"area":"rag"},{"id":"2602.11156","title":"HybridRAG: A Practical LLM-based ChatBot Framework based on Pre-Generated Q&A over Raw Unstructured Documents","created":"2025-11-30","cited_by_count":0,"area":"rag"},{"id":"2603.18409","title":"TopoChunker: Topology-Aware Agentic Document Chunking Framework","created":"2026-03-19","cited_by_count":0,"area":"rag"},{"id":"2605.00911","title":"When Good OCR Is Not Enough: Benchmarking OCR Robustness for Retrieval-Augmented Generation","created":"2026-04-29","cited_by_count":0,"area":"rag"},{"id":"2605.19309","title":"How Do Document Parsers Break? Auditing Structural Vulnerability in Document Intelligence","created":"2026-05-19","cited_by_count":0,"area":"rag"},{"id":"2607.18102","title":"FinSAgent: Corpus-Aligned Multi-Agent RAG Framework for Evidence-Grounded SEC Filing Question Answering","created":"2026-07-20","cited_by_count":0,"area":"rag"},{"id":"2608.14032","title":"HAM-RAG: Hierarchy-Aware Multimodal RAG for Structure-Faithful Interleaved Generation","created":"2026-08-14","cited_by_count":0,"area":"rag"}],"next_cursor":null}