{"total":18,"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":"2411.04952","title":"M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding","created":"2024-11-07","cited_by_count":111,"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":"2505.16470","title":"Benchmarking Retrieval-Augmented Multimodal Generation for Document Question Answering","created":"2025-05-22","cited_by_count":36,"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":"2505.05666","title":"Lost in OCR Translation? Vision-Based Approaches to Robust Document Retrieval","created":"2025-05-08","cited_by_count":11,"area":"rag"},{"id":"2602.03992","title":"Nemotron ColEmbed V2: Top-Performing Late Interaction Embedding Models for Visual Document Retrieval","created":"2026-02-03","cited_by_count":10,"area":"rag"},{"id":"2511.00903","title":"ColMate: Contrastive Late Interaction and Masked Text for Multimodal Document Retrieval","created":"2025-11-02","cited_by_count":4,"area":"rag"},{"id":"2405.20245","title":"Retrieval Augmented Structured Generation: Business Document Information Extraction As Tool Use","created":"2024-05-30","cited_by_count":3,"area":"rag"},{"id":"2601.03262","title":"Roles of MLLMs in Visually Rich Document Retrieval for RAG: A Survey","created":"2025-12-16","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":"2509.02123","title":"CMRAG: Co-modality-based visual document retrieval and question answering","created":"2025-09-02","cited_by_count":1,"area":"rag"},{"id":"2511.06582","title":"TabRAG: Improving Tabular Document Question Answering for Retrieval Augmented Generation via Structured Representations","created":"2025-11-10","cited_by_count":1,"area":"rag"},{"id":"2603.04238","title":"Retrieval or Representation? Reassessing Benchmark Gaps in Multilingual and Visually Rich RAG","created":"2026-03-04","cited_by_count":0,"area":"rag"},{"id":"2603.14170","title":"Citation-Enforced RAG for Fiscal Document Intelligence: Cited, Explainable Knowledge Retrieval in Tax Compliance","created":"2026-03-11","cited_by_count":0,"area":"rag"},{"id":"2607.24554","title":"DeCoRAG: Cognitive Decoupling and Semantic-Aware Cropping for Complex Document Understanding","created":"2026-07-27","cited_by_count":0,"area":"rag"},{"id":"2608.12335","title":"HC-RAG: Evidence-Centric Retrieval-Augmented Generation over Heterogeneous Financial Filings","created":"2026-06-03","cited_by_count":0,"area":"rag"},{"id":"2608.21792","title":"HIRA: A Human-in-the-Loop Retrieval-Augmented Cascade for Document Classification in Regulated Industries","created":"2026-08-22","cited_by_count":0,"area":"rag"}],"next_cursor":null}