Trust Before Fusion: QIMG-7 and Source-Aware Resolution for Polluted Multimodal RAG

arXiv:2607.10798 · cs.CL · Submitted 2026-07-12 · Read on arXiv

cs.CL

Submitted: 2026-07-12

Updated: 2026-10-18

Comments: 23 pages, 6 figures, 23 tables. Preprint under review

Code: https://github.com/SaadElDine/Trust_Before_Fusion

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• RAG — 2× in this paper · explained in 3 episodes
• Ablation — 1× in this paper · explained in 1 episode
• Benchmark — 1× in this paper · explained in 2 episodes
• Generator — 1× in this paper · explained in 2 episodes
• Multimodal Fusion — 1× in this paper · explained in 4 episodes
• Retrieval-Augmented Generation (RAG) — 1× in this paper · explained in 19 episodes

Sources

• Qwen2.5-VL Technical Report
• MIRAGE: Defending Long-Form RAG Against Misinformation Pollution
• MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Poisoning Attacks
• Poisoned-MRAG: Knowledge Poisoning Attacks to Multimodal Retrieval Augmented Generation
• RAG-Check: Evaluating Multimodal Retrieval Augmented Generation Performance
• Corrective Retrieval Augmented Generation

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering