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

arXiv: https://arxiv.org/abs/2605.15019 · HTML: https://mlsanity.com/paper/2605.15019/

## Key facts

- Cited by 1 papers in the map (data through 14 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.

## Placed in

- Retrieval-augmented generation / [Multimodal RAG](https://mlsanity.com/rag/multimodal-rag/)

## Builds on (most cited first, 30 of 33)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [OK-VQA: A Visual Question Answering Benchmark Requiring External Knowledge](https://mlsanity.com/paper/1906.00067/) (2019)
- [Kosmos-2: Grounding Multimodal Large Language Models to the World](https://mlsanity.com/paper/2306.14824/) (2023)
- [A-OKVQA: A Benchmark for Visual Question Answering using World Knowledge](https://mlsanity.com/paper/2206.01718/) (2022)
- [YOLO-World: Real-Time Open-Vocabulary Object Detection](https://mlsanity.com/paper/2401.17270/) (2024)
- [VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents](https://mlsanity.com/paper/2410.10594/) (2024)
- [MuRAG: Multimodal Retrieval-Augmented Generator for Open Question Answering over Images and Text](https://mlsanity.com/paper/2210.02928/) (2022)
- [Can Pre-trained Vision and Language Models Answer Visual Information-Seeking Questions?](https://mlsanity.com/paper/2302.11713/) (2023)
- [MMLongBench-Doc: Benchmarking Long-context Document Understanding with Visualizations](https://mlsanity.com/paper/2407.01523/) (2024)
- [M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding](https://mlsanity.com/paper/2411.04952/) (2024)
- [Encyclopedic VQA: Visual questions about detailed properties of fine-grained categories](https://mlsanity.com/paper/2306.09224/) (2023)
- [SPIQA: A Dataset for Multimodal Question Answering on Scientific Papers](https://mlsanity.com/paper/2407.09413/) (2024)
- [GROUNDHOG: Grounding Large Language Models to Holistic Segmentation](https://mlsanity.com/paper/2402.16846/) (2024)
- [VISTA: Visualized Text Embedding For Universal Multi-Modal Retrieval](https://mlsanity.com/paper/2406.04292/) (2024)
- [EchoSight: Advancing Visual-Language Models with Wiki Knowledge](https://mlsanity.com/paper/2407.12735/) (2024)
- [Universal Vision-Language Dense Retrieval: Learning A Unified Representation Space for Multi-Modal Retrieval](https://mlsanity.com/paper/2209.00179/) (2022)
- [MMDocIR: Benchmarking Multimodal Retrieval for Long Documents](https://mlsanity.com/paper/2501.08828/) (2025)
- [PreFLMR: Scaling Up Fine-Grained Late-Interaction Multi-modal Retrievers](https://mlsanity.com/paper/2402.08327/) (2024)
- [M-Longdoc: A Benchmark For Multimodal Super-Long Document Understanding And A Retrieval-Aware Tuning Framework](https://mlsanity.com/paper/2411.06176/) (2024)
- [REAL-MM-RAG: A Real-World Multi-Modal Retrieval Benchmark](https://mlsanity.com/paper/2502.12342/) (2025)
- [VISA: Retrieval Augmented Generation with Visual Source Attribution](https://mlsanity.com/paper/2412.14457/) (2024)
- [MARVEL: Unlocking the Multi-Modal Capability of Dense Retrieval via Visual Module Plugin](https://mlsanity.com/paper/2310.14037/) (2023)
- [MORE: Multi-mOdal REtrieval Augmented Generative Commonsense Reasoning](https://mlsanity.com/paper/2402.13625/) (2024)
- [Toloka Visual Question Answering Benchmark](https://mlsanity.com/paper/2309.16511/) (2023)
- [OMGM: Orchestrate Multiple Granularities and Modalities for Efficient Multimodal Retrieval](https://mlsanity.com/paper/2505.07879/) (2025)
- [SGIC: A Self-Guided Iterative Calibration Framework for RAG](https://mlsanity.com/paper/2506.16172/) (2025)

## Built on by (most cited first, 1 of 1)

- [How Is Automated Research Evaluated? A Survey of Benchmarks and Evaluation Practices](https://mlsanity.com/paper/2610.11877/) (2026)

## 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.