mlsanityData to 7 Oct 2026

SuperRAG: Beyond RAG with Layout-Aware Graph Modeling

arXiv 2503.04790 ↗First posted 28 Feb 2025cs.CL cs.AIcited by 9

On the map: Retrieval-augmented generation → Multimodal RAG

Abstract (arXiv)

This paper introduces layout-aware graph modeling for multimodal RAG. Different from traditional RAG methods that mostly deal with flat text chunks, the proposed method takes into account the relationship of multimodalities by using a graph structure. To do that, a graph modeling structure is defined based on document layout parsing. The structure of an input document is retained with the connection of text chunks, tables, and figures. This representation allows the method to handle complex questions that require information from multimodalities. To confirm the efficiency of the graph modeling, a flexible RAG pipeline is developed using robust components. Experimental results on four benchmark test sets confirm the contribution of the layout-aware modeling for performance improvement of the RAG pipeline.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation. Builds on 27 of its 36 references that are in the map. First posted on arXiv 28 Feb 2025.

Builds on

27 of 36 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents14 Oct

Other references · 26

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2020REALM: Retrieval-Augmented Language Model Pre-Trainingcited by 2,126
  3. 2024From Local to Global: A Graph RAG Approach to Query-Focused Summarizationcited by 1,411
  4. 2020Leveraging Passage Retrieval with Generative Models for Open Domain Question Answeringcited by 1,203
  5. 2022Atlas: Few-shot Learning with Retrieval Augmented Language Modelscited by 940
  6. 2022Interleaving Retrieval with Chain-of-Thought Reasoning for Knowledge-Intensive Multi-Step Questionscited by 911
  7. 2023REPLUG: Retrieval-Augmented Black-Box Language Modelscited by 786
  8. 2021The Curious Case of Hallucinations in Neural Machine Translationcited by 161
  9. 2022DocPrompting: Generating Code by Retrieving the Docscited by 151
  10. 2023Knowledge Graph Prompting for Multi-Document Question Answeringcited by 150
  11. 2023Investigating the Factual Knowledge Boundary of Large Language Models with Retrieval Augmentationcited by 146
  12. 2022Rethinking with Retrieval: Faithful Large Language Model Inferencecited by 145
14 more
  1. 2023Walking Down the Memory Maze: Beyond Context Limit through Interactive Readingcited by 129
  2. 2024GNN-RAG: Graph Neural Retrieval for Large Language Model Reasoningcited by 128
  3. 2020Factual Error Correction for Abstractive Summarization Modelscited by 108
  4. 2023Retrieving Multimodal Information for Augmented Generation: A Surveycited by 84
  5. 2021LayoutReader: Pre-training of Text and Layout for Reading Order Detectioncited by 79
  6. 2020End-to-End Object Detection with Fully Convolutional Networkcited by 70
  7. 2024SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMscited by 67
  8. 2023PDFTriage: Question Answering over Long, Structured Documentscited by 29
  9. 2024HOLMES: Hyper-Relational Knowledge Graphs for Multi-hop Question Answering using LLMscited by 24
  10. 2020Prototype-to-Style: Dialogue Generation with Style-Aware Editing on Retrieval Memorycited by 22
  11. 2024Multi-Head RAG: Solving Multi-Aspect Problems with LLMscited by 18
  12. 2021Transductive Learning for Unsupervised Text Style Transfercited by 12
  13. 2024Docs2KG: Unified Knowledge Graph Construction from Heterogeneous Documents Assisted by Large Language Modelscited by 9
  14. 2023AutoRepo: A general framework for multi-modal LLM-based automated construction reportingcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 4; 2026: 5.

9 papers.

  1. 2025BookRAG: A Hierarchical Structure-aware Index-based Approach for Retrieval-Augmented Generation on Complex Documentscited by 16
  2. 2025ORANSight-2.0: Foundational LLMs for O-RANcited by 13
  3. 2025LAD-RAG: Layout-aware Dynamic RAG for Visually-Rich Document Understandingcited by 7
  4. 2026MoDora: Tree-Based Semi-Structured Document Analysis Systemcited by 3
  5. 2026SF-RAG: Structure-Fidelity Retrieval-Augmented Generation for Academic Question Answeringcited by 2
  6. 2025CMRAG: Co-modality-based visual document retrieval and question answeringcited by 1
  7. 2026Continual Fine-Tuning of Large Language Models via Program Memorycited by 1
  8. 2026ColGraphRAG: Late-Interaction Evidence Retrieval for Multimodal GraphRAGcited by 0
  9. 2026EidosDoc: Implicit Structure Encoding for Cost-Effective Semi-Structured Document QAcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Vision-Guided Chunking Is All You Need: Enhancing RAG with Multimodal Document Understanding
  2. 2026Multimodal Graph RAG for Long-range Visually Rich Document Understanding
  3. 2026LFRAG: Layout-oriented Fine-grained Retrieval-Augmented Generation on Multimodal Document Understanding
  4. 2025Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding
  5. 2025SCAN: Semantic Document Layout Analysis for Textual and Visual Retrieval-Augmented Generation
  6. 2024LayoutLLM: Layout Instruction Tuning with Large Language Models for Document Understanding
  7. 2025MMDocIR: Benchmarking Multimodal Retrieval for Long Documents
  8. 2025RAG vs. GraphRAG: A Systematic Evaluation and Key Insights