mlsanityData to 7 Oct 2026

From Scenes to Elements: Multi-Granularity Evidence Retrieval for Verifiable Multimodal RAG

arXiv 2605.15019 ↗First posted 14 May 2026cs.CLcited by 1

On the map: Retrieval-augmented generation → Multimodal RAG

Abstract (arXiv)

Multimodal Retrieval-Augmented Generation (RAG) systems retrieve evidence at coarse granularities (entire images or scenes), creating a mismatch with fine-grained user queries and making failures unverifiable. We introduce GranuVistaVQA, a multimodal benchmark featuring real-world landmarks with element-level annotations across multiple viewpoints, capturing the partial observation challenge where individual images contain only subsets of entities. We further propose GranuRAG, a multi-granularity framework that treats visual elements as first-class retrieval units through three stages: element-level detection and classification, multi-granularity cross-modal alignment for evidence retrieval, and attribution-constrained generation. By grounding retrieval at the element level rather than relying on implicit attention, our approach enables transparent error diagnosis. Experiments demonstrate that GranuRAG achieves up to 29.2% improvement over six strong baselines for this task.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation. Builds on 33 of its 64 references that are in the map. First posted on arXiv 14 May 2026.

Builds on

33 of 64 references.

Closest ancestors · 9

Same direction, newest first

  1. 2025Taming a Retrieval Framework to Read Images in Humanlike Manner for Augmenting Generation of MLLMs12 Oct
  2. 2025OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal Retrieval10 May
  3. 2025A Multi-Granularity Retrieval Framework for Visually-Rich Documents1 May
  4. 2024VISA: Retrieval Augmented Generation with Visual Source Attribution19 Dec
  5. 2024M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding7 Nov
  6. 2024VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents14 Oct
  7. 2024MORE: Multi-mOdal REtrieval Augmented Generative Commonsense Reasoning21 Feb
  8. 2023Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories15 Jun
  9. 2022MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text6 Oct

Other references · 24

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  4. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,462
  5. 2023Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detectioncited by 3,274
  6. 2019OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledgecited by 1,114
  7. 2023Kosmos-2: Grounding Multimodal Large Language Models to the Worldcited by 1,075
  8. 2022A-OKVQA: A Benchmark for Visual Question Answering using World Knowledgecited by 702
  9. 2024YOLO-World: Real-Time Open-Vocabulary Object Detectioncited by 498
  10. 2023Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?cited by 203
  11. 2024MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizationscited by 174
  12. 2024SPIQA: A Dataset for Multimodal Question Answering on Scientific Paperscited by 75
12 more
  1. 2024GROUNDHOG: Grounding Large Language Models to Holistic Segmentationcited by 70
  2. 2024VISTA: Visualized Text Embedding For Universal Multi-Modal Retrievalcited by 67
  3. 2024EchoSight: Advancing Visual-Language Models with Wiki Knowledgecited by 61
  4. 2022Universal Vision-Language Dense Retrieval: Learning A Unified Representation Space for Multi-Modal Retrievalcited by 57
  5. 2025MMDocIR: Benchmarking Multimodal Retrieval for Long Documentscited by 43
  6. 2024PreFLMR: Scaling Up Fine-Grained Late-Interaction Multi-modal Retrieverscited by 42
  7. 2024M-Longdoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Frameworkcited by 36
  8. 2025REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmarkcited by 34
  9. 2023MARVEL: Unlocking the Multi-Modal Capability of Dense Retrieval via Visual Module Plugincited by 22
  10. 2023Toloka Visual Question Answering Benchmarkcited by 10
  11. 2025SGIC: A Self-Guided Iterative Calibration Framework for RAGcited by 8
  12. 2025Not All LoRA Parameters Are Essential: Insights on Inference Necessitycited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026How Is Automated Research Evaluated? A Survey of Benchmarks and Evaluation Practicescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026MG2-RAG: Multi-Granularity Graph for Multimodal Retrieval-Augmented Generation
  2. 2026CANOPY: Adaptive-Granularity Evidence Compression for Multimodal RAG ↗
  3. 2026Coarse Indexing, Fine Evidence: Decoupling Temporal Granularity in Long-Video RAG
  4. 2026ARK: A Dual-Axis Multimodal Retrieval Benchmark along Reasoning and Knowledge
  5. 2026Utility-Oriented Visual Evidence Selection for Multimodal Retrieval-Augmented Generation
  6. 2026Purifying Multimodal Retrieval: Fragment-Level Evidence Selection for RAG
  7. 2026BayesRAG: Probabilistic Mutual Evidence Corroboration for Multimodal Retrieval-Augmented Generation
  8. 2025Visual-RAG: Benchmarking Text-to-Image Retrieval Augmented Generation for Visual Knowledge Intensive Queries