{"ID":6536237,"CreatedAt":"2026-07-14T01:21:01.169441415Z","UpdatedAt":"2026-07-15T03:28:55.185153975Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.10798","arxiv_id":"2607.10798","title":"Trust Before Fusion: QIMG-7 and Source-Aware Resolution for Polluted Multimodal RAG","abstract":"Multimodal retrieval-augmented generation (RAG) is often evaluated with clean evidence, yet real retrieval can return topically relevant but unreliable content: false text and misleading images from corrupted metadata, entity swaps, typographic overlays, semantic edits, adversarial patches, blends, or style transfer. We introduce QIMG-7, a controlled benchmark for multimodal retrieval pollution in multi-sentence factual QA, spanning four datasets, seven image-attack families, and 16 paired clean/polluted regimes, for 1,760 evaluation rows per method. Across four generator/gate stacks, naive multimodal fusion is brittle: in the main gpt-4o-mini stack, Full-MM support drops from 0.908 with clean text to 0.490 with polluted text, often making Parametric fallback safer than retrieval. We propose source-aware trust resolution (SATR), a training-free approach that compares Parametric, Text-only, and Full-MM candidate answers and selects among candidate answers or falls back based on source reliability. The Field-Selector variant achieves the best balanced score, 0.816, improving over Full-MM by 11.7 points and over the Cascaded Router by 2.7 points. Ablations show that, in this text-first setting, explicit text-reliability modeling is the dominant driver of these gains. Overall, in text-first factual QA with multimodal retrieval conflict, our results support selective trust rather than unconditional fusion. Artifacts are available at https://github.com/SaadElDine/Trust_Before_Fusion.","short_abstract":"Multimodal retrieval-augmented generation (RAG) is often evaluated with clean evidence, yet real retrieval can return topically relevant but unreliable content: false text and misleading images from corrupted metadata, entity swaps, typographic overlays, semantic edits, adversarial patches, blends, or style transfer. W...","url_abs":"https://arxiv.org/abs/2607.10798","url_pdf":"https://arxiv.org/pdf/2607.10798v1","authors":"[\"Saadeldine Eletter\",\"Owais Aijaz\",\"Preslav Nakov\"]","published":"2026-07-12T15:13:09Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"RAG\"]","has_code":false,"code_links":[{"ID":614150,"CreatedAt":"2026-07-14T01:21:01.169441415Z","UpdatedAt":"2026-07-14T01:21:01.169441415Z","DeletedAt":null,"paper_id":6536237,"paper_url":"https://arxiv.org/abs/2607.10798","paper_title":"Trust Before Fusion: QIMG-7 and Source-Aware Resolution for Polluted Multimodal RAG","repo_url":"https://github.com/SaadElDine/Trust_Before_Fusion","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}