Research map / Vision-language and multimodal / Visual question answering
MR-RAG: Multimodal Relevance-Aware Retrieval-Augmented Generation for Medical Visual Question Answering
Xuze Li, Haozhao Wang, Zhenyu Huang, Zhongxu Wang, Jinghua Zhang, Ruixuan Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| replace single image-to-text retrieval with multimodal cooperative retrieval (MCR) (ablation) | LLaVA-Med-1.5 RAG · Average of three medical VQA datasets | F1 (%): 69.61 -> 73.34 | Improved |
| add importance-aware information flow augmentation (IFA) on top of MCR (ablation) | MR-RAG · Average of three medical VQA datasets | F1 (%): 73.34 -> 75.33 | Improved |
| use fused multi-score retrieval instead of single-score similarity (ablation) | MCR · Retrieval similarity ablation | accuracy (%): 77.51 -> 81.95 (vs best single I2T) | Improved |
| use text-to-image similarity alone for retrieval (ablation) | MCR · Retrieval similarity ablation | accuracy (%): 77.51 -> 64.71 (vs I2T) | Hurt |
| mix in more irrelevant documents (up to half of input) | LLaVA-Med-1.5 RAG · Noise analysis | accuracy (%): 77.9 -> 68.1 | Hurt |
| block attention flow Reports to Question in shallow-to-mid layers (ablation) | LLaVA-Med-1.5 · IU-Xray | accuracy difference | Hurt |
| block attention flow Reports to Image or Reports to Last (ablation) | LLaVA-Med-1.5 · IU-Xray | accuracy difference | No clear effect |
| apply MR-RAG instead of beam search/greedy across retrieval sizes K from 5 to 30 | MR-RAG · Harvard-FairVLMed | accuracy range across K: beam search 65.2%-73.8% vs MR-RAG 79.5%-82.1% | Improved |
| add MMed-RAG retrieval and preference alignment to LLaVA-Med-1.5 | LLaVA-Med-1.5 · Harvard-FairVLMed | accuracy (%): 77.35 -> 70.57 | Hurt |
| add VCD decoding to LLaVA-Med-1.5 | LLaVA-Med-1.5 · MIMIC-CXR | accuracy (%): 71.92 -> 65.35 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- MMed-RAG — MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models (ICLR 2025) · better on 2 of 2 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- MMed-RAG: Versatile Multimodal RAG System for Medical Vision Language Models (ICLR 2025 · similarity 0.90)
- MRAG-Bench: Vision-Centric Evaluation for Retrieval-Augmented Multimodal Models (ICLR 2025 · similarity 0.90)
- Document Haystacks: Vision-Language Reasoning Over Piles of 1000+ Documents (CVPR 2025 · similarity 0.90)
- RAG-IGBench: Innovative Evaluation for RAG-based Interleaved Generation in Open-domain Question Answering (NeurIPS 2025 · similarity 0.89)
- SV-RAG: LoRA-Contextualizing Adaptation of MLLMs for Long Document Understanding (ICLR 2025 · similarity 0.89)
- Benchmarking Retrieval-Augmented Multimomal Generation for Document Question Answering (NeurIPS 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
