mlsanityData to 7 Oct 2026

VISA: Retrieval Augmented Generation with Visual Source Attribution

arXiv 2412.14457 ↗First posted 19 Dec 2024cs.IRcited by 28

On the map: Retrieval-augmented generation → Multimodal RAG

Abstract (arXiv)

Generation with source attribution is important for enhancing the verifiability of retrieval-augmented generation (RAG) systems. However, existing approaches in RAG primarily link generated content to document-level references, making it challenging for users to locate evidence among multiple content-rich retrieved documents. To address this challenge, we propose Retrieval-Augmented Generation with Visual Source Attribution (VISA), a novel approach that combines answer generation with visual source attribution. Leveraging large vision-language models (VLMs), VISA identifies the evidence and highlights the exact regions that support the generated answers with bounding boxes in the retrieved document screenshots. To evaluate its effectiveness, we curated two datasets: Wiki-VISA, based on crawled Wikipedia webpage screenshots, and Paper-VISA, derived from PubLayNet and tailored to the medical domain. Experimental results demonstrate the effectiveness of VISA for visual source attribution on documents' original look, as well as highlighting the challenges for improvement. Code, data, and model checkpoints will be released.

Key facts. Cited by 28 papers in the map (data through 7 Oct 2026). Placed in Multimodal RAG, one of 15 directions in Retrieval-augmented generation. Builds on 14 of its 36 references that are in the map. First posted on arXiv 19 Dec 2024.

Builds on

14 of 36 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024M3DocRAG: Multi-modal Retrieval is What You Need for Multi-page Multi-document Understanding7 Nov
  2. 2024Beyond Text: Optimizing RAG with Multimodal Inputs for Industrial Applications29 Oct
  3. 2024VisRAG: Vision-based Retrieval-augmented Generation on Multi-modality Documents14 Oct

Other references · 11

  1. 2024GPT-4o System Cardcited by 4,467
  2. 2024Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolutioncited by 4,151
  3. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,185
  4. 2024The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scalecited by 1,104
  5. 2019Object Detection in 20 Years: A Surveycited by 528
  6. 2018Object Detection with Deep Learning: A Reviewcited by 524
  7. 2024PaliGemma 2: A Family of Versatile VLMs for Transfercited by 204
  8. 2024ColPali: Efficient Document Retrieval with Vision Language Modelscited by 190
  9. 2022Attributed Question Answering: Evaluation and Modeling for Attributed Large Language Modelscited by 108
  10. 2024MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Modelscited by 84
  11. 2024Reliable, Adaptable, and Attributable Language Models with Retrievalcited by 73

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2025: 14; 2026: 14.

28 papers.

Sort:

By area:

  1. 2025Pixel Reasoner: Incentivizing Pixel-Space Reasoning with Curiosity-Driven Reinforcement Learningcited by 267
  2. 2025MDocAgent: A Multi-Modal Multi-Agent Framework for Document Understandingcited by 66
  3. 2025VDocRAG: Retrieval-Augmented Generation over Visually-Rich Documentscited by 57
  4. 2025Ask in Any Modality: A Comprehensive Survey on Multimodal Retrieval-Augmented Generationcited by 42
  5. 2025SimpleDoc: Multi-Modal Document Understanding with Dual-Cue Page Retrieval and Iterative Refinementcited by 27
  6. 2025Toward Generalizable Evaluation in the LLM Era: A Survey Beyond Benchmarkscited by 26
  7. 2026ViDoRe V3: A Comprehensive Evaluation of Retrieval Augmented Generation in Complex Real-World Scenarioscited by 22
  8. 2025MoLoRAG: Bootstrapping Document Understanding via Multi-modal Logic-aware Retrievalcited by 17
  9. 2025FinRAGBench-V: A Benchmark for Multimodal RAG with Visual Citation in the Financial Domaincited by 16
  10. 2025DocLens : A Tool-Augmented Multi-Agent Framework for Long Visual Document Understandingcited by 15
  11. 2025Attribution, Citation, and Quotation: A Survey of Evidence-based Text Generation with Large Language Modelscited by 7
  12. 2026CiteVQA: Benchmarking Evidence Attribution for Trustworthy Document Intelligencecited by 5
16 more
  1. 2025Follow the Flow: Fine-grained Flowchart Attribution with Neurosymbolic Agentscited by 4
  2. 2025Look as You Think: Unifying Reasoning and Visual Evidence Attribution for Verifiable Document RAG via Reinforcement Learningcited by 3
  3. 2026Magic-MM-Embedding: Towards Visual-Token-Efficient Universal Multimodal Embedding with MLLMscited by 3
  4. 2025Empowering Multimodal LLMs with External Tools: A Comprehensive Surveycited by 2
  5. 2025M3DR: Towards Universal Multilingual Multimodal Document Retrievalcited by 2
  6. 2026From Scenes to Elements: Multi-Granularity Evidence Retrieval for Verifiable Multimodal RAGcited by 1
  7. 2026Index Light, Reason Deep: Deferred Visual Ingestion for Visual-Dense Document Question Answeringcited by 0
  8. 2026Chain of Evidence: Pixel-Level Visual Attribution for Iterative Retrieval-Augmented Generationcited by 0
  9. 2026VinQA: Visual Elements Interleaved Long-form Answer Generation for Real-World Multimodal Document QAcited by 0
  10. 2026MultAttnAttrib: Training-Free Multimodal Attribution in Long Document Question Answeringcited by 0
  11. 2026CMDR: Contextual Multimodal Document Retrievalcited by 0
  12. 2026Evidence Attribution in Visual Document Understanding without Coordinates or Region Labelscited by 0
  13. 2026Valid Per-Field Selective Risk Control for Document Extraction: Three Failure Modes, a Validity Ladder, and When Conditioning Payscited by 0
  14. 2026MCite-RL: Towards Reliable Multimodal RAG via Citation-enhanced Agentic Reinforcement Learningcited by 0
  15. 2026MIDR: Enrichment-Augmented Indexing for Multimodal Document Retrievalcited by 0
  16. 2026DocAttriBench: Benchmarking Answer Grounding in Document Visual Question Answeringcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025VeriCite: Towards Reliable Citations in Retrieval-Augmented Generation via Rigorous Verification
  2. 2025Visual-RAG: Benchmarking Text-to-Image Retrieval Augmented Generation for Visual Knowledge Intensive Queries
  3. 2025Concise and Sufficient Sub-Sentence Citations for Retrieval-Augmented Generation
  4. 2024Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation
  5. 2025Enhancing Document VQA Models via Retrieval-Augmented Generation
  6. 2026Does More Retrieved Evidence Help Visual Retrieval-Augmented Generation with Diffusion Language Models?
  7. 2025Are We on the Right Way for Assessing Document Retrieval-Augmented Generation?
  8. 2024RAGViz: Diagnose and Visualize Retrieval-Augmented Generation