@inproceedings{eletter-etal-2026-trust,
title = "Trust Before Fusion: {QIMG}-7 and Source-Aware Resolution for Polluted Multimodal {RAG}",
author = "Eletter, Saadeldine and
Aijaz, Owais and
Nakov, Preslav",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-main.1720/",
pages = "39236--39261",
ISBN = "979-8-89176-459-0",
abstract = "Multimodal retrieval-augmented generation (RAG) is usually evaluated with clean evidence, although deployed systems may retrieve topically relevant but unreliable text or images. We introduce QIMG-7, a controlled post-retrieval stress test for multi-sentence factual QA comprising 110 questions from four datasets, seven visual-evidence pollution families, and 16 paired clean/polluted regimes per question (1,760 rows per method). Across four generator/gate stacks, Full-MM is fragile under polluted text: in the main gpt-4o-mini stack, support decreases from 0.908 with clean text to 0.490 with polluted text. We propose source-aware trust resolution (SATR), a training-free family that compares Parametric, Text-only, and Full-MM candidate answers and selectively chooses a branch or falls back. Field-Selector obtains the highest numerical balanced score, 0.816, improving over Full-MM by 11.7 points and the Cascaded Router by 2.2 points. TextTrust, an image-blind text-reliability baseline, reaches 0.800; Field-Selector{'}s 1.5-point balanced advantage over it is not statistically resolved (95{\%} CI [-0.006, 0.036]). In this text-first setting, the results support selective trust rather than unconditional multimodal fusion. Artifacts are available at https://github.com/mbzuai-nlp/Trust{\_}Before{\_}Fusion."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="eletter-etal-2026-trust">
<titleInfo>
<title>Trust Before Fusion: QIMG-7 and Source-Aware Resolution for Polluted Multimodal RAG</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saadeldine</namePart>
<namePart type="family">Eletter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Owais</namePart>
<namePart type="family">Aijaz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-459-0</identifier>
</relatedItem>
<abstract>Multimodal retrieval-augmented generation (RAG) is usually evaluated with clean evidence, although deployed systems may retrieve topically relevant but unreliable text or images. We introduce QIMG-7, a controlled post-retrieval stress test for multi-sentence factual QA comprising 110 questions from four datasets, seven visual-evidence pollution families, and 16 paired clean/polluted regimes per question (1,760 rows per method). Across four generator/gate stacks, Full-MM is fragile under polluted text: in the main gpt-4o-mini stack, support decreases from 0.908 with clean text to 0.490 with polluted text. We propose source-aware trust resolution (SATR), a training-free family that compares Parametric, Text-only, and Full-MM candidate answers and selectively chooses a branch or falls back. Field-Selector obtains the highest numerical balanced score, 0.816, improving over Full-MM by 11.7 points and the Cascaded Router by 2.2 points. TextTrust, an image-blind text-reliability baseline, reaches 0.800; Field-Selector’s 1.5-point balanced advantage over it is not statistically resolved (95% CI [-0.006, 0.036]). In this text-first setting, the results support selective trust rather than unconditional multimodal fusion. Artifacts are available at https://github.com/mbzuai-nlp/Trust_Before_Fusion.</abstract>
<identifier type="citekey">eletter-etal-2026-trust</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-main.1720/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>39236</start>
<end>39261</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Trust Before Fusion: QIMG-7 and Source-Aware Resolution for Polluted Multimodal RAG
%A Eletter, Saadeldine
%A Aijaz, Owais
%A Nakov, Preslav
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-459-0
%F eletter-etal-2026-trust
%X Multimodal retrieval-augmented generation (RAG) is usually evaluated with clean evidence, although deployed systems may retrieve topically relevant but unreliable text or images. We introduce QIMG-7, a controlled post-retrieval stress test for multi-sentence factual QA comprising 110 questions from four datasets, seven visual-evidence pollution families, and 16 paired clean/polluted regimes per question (1,760 rows per method). Across four generator/gate stacks, Full-MM is fragile under polluted text: in the main gpt-4o-mini stack, support decreases from 0.908 with clean text to 0.490 with polluted text. We propose source-aware trust resolution (SATR), a training-free family that compares Parametric, Text-only, and Full-MM candidate answers and selectively chooses a branch or falls back. Field-Selector obtains the highest numerical balanced score, 0.816, improving over Full-MM by 11.7 points and the Cascaded Router by 2.2 points. TextTrust, an image-blind text-reliability baseline, reaches 0.800; Field-Selector’s 1.5-point balanced advantage over it is not statistically resolved (95% CI [-0.006, 0.036]). In this text-first setting, the results support selective trust rather than unconditional multimodal fusion. Artifacts are available at https://github.com/mbzuai-nlp/Trust_Before_Fusion.
%U https://aclanthology.org/2026.emnlp-main.1720/
%P 39236-39261
Markdown (Informal)
[Trust Before Fusion: QIMG-7 and Source-Aware Resolution for Polluted Multimodal RAG](https://aclanthology.org/2026.emnlp-main.1720/) (Eletter et al., EMNLP 2026)
ACL