@inproceedings{li-etal-2025-cmie,
title = "{CMIE}: Combining {MLLM} Insights with External Evidence for Explainable Out-of-Context Misinformation Detection",
author = "Li, Fanxiao and
Wu, Jiaying and
He, Canyuan and
Zhou, Wei",
editor = "Che, Wanxiang and
Nabende, Joyce and
Shutova, Ekaterina and
Pilehvar, Mohammad Taher",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.findings-acl.487/",
doi = "10.18653/v1/2025.findings-acl.487",
pages = "9342--9354",
ISBN = "979-8-89176-256-5",
abstract = "Multimodal large language models (MLLMs) have demonstrated impressive capabilities in visual reasoning and text generation. While previous studies have explored the application of MLLM for detecting out-of-context (OOC) misinformation, our empirical analysis reveals two persisting challenges of this paradigm. Evaluating the representative GPT-4o model on direct reasoning and evidence augmented reasoning, results indicate that MLLM struggle to capture the deeper relationships{---}specifically, cases in which the image and text are not directly connected but are associated through underlying semantic links. Moreover, noise in the evidence further impairs detection accuracy.To address these challenges, we propose CMIE, a novel OOC misinformation detection framework that incorporates a Coexistence Relationship Generation (CRG) strategy and an Association Scoring (AS) mechanism. CMIE identifies the underlying coexistence relationships between images and text, and selectively utilizes relevant evidence to enhance misinformation detection. Experimental results demonstrate that our approach outperforms existing methods."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2025-cmie">
<titleInfo>
<title>CMIE: Combining MLLM Insights with External Evidence for Explainable Out-of-Context Misinformation Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fanxiao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaying</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Canyuan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2025</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Nabende</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Taher</namePart>
<namePart type="family">Pilehvar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-256-5</identifier>
</relatedItem>
<abstract>Multimodal large language models (MLLMs) have demonstrated impressive capabilities in visual reasoning and text generation. While previous studies have explored the application of MLLM for detecting out-of-context (OOC) misinformation, our empirical analysis reveals two persisting challenges of this paradigm. Evaluating the representative GPT-4o model on direct reasoning and evidence augmented reasoning, results indicate that MLLM struggle to capture the deeper relationships—specifically, cases in which the image and text are not directly connected but are associated through underlying semantic links. Moreover, noise in the evidence further impairs detection accuracy.To address these challenges, we propose CMIE, a novel OOC misinformation detection framework that incorporates a Coexistence Relationship Generation (CRG) strategy and an Association Scoring (AS) mechanism. CMIE identifies the underlying coexistence relationships between images and text, and selectively utilizes relevant evidence to enhance misinformation detection. Experimental results demonstrate that our approach outperforms existing methods.</abstract>
<identifier type="citekey">li-etal-2025-cmie</identifier>
<identifier type="doi">10.18653/v1/2025.findings-acl.487</identifier>
<location>
<url>https://aclanthology.org/2025.findings-acl.487/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>9342</start>
<end>9354</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CMIE: Combining MLLM Insights with External Evidence for Explainable Out-of-Context Misinformation Detection
%A Li, Fanxiao
%A Wu, Jiaying
%A He, Canyuan
%A Zhou, Wei
%Y Che, Wanxiang
%Y Nabende, Joyce
%Y Shutova, Ekaterina
%Y Pilehvar, Mohammad Taher
%S Findings of the Association for Computational Linguistics: ACL 2025
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-256-5
%F li-etal-2025-cmie
%X Multimodal large language models (MLLMs) have demonstrated impressive capabilities in visual reasoning and text generation. While previous studies have explored the application of MLLM for detecting out-of-context (OOC) misinformation, our empirical analysis reveals two persisting challenges of this paradigm. Evaluating the representative GPT-4o model on direct reasoning and evidence augmented reasoning, results indicate that MLLM struggle to capture the deeper relationships—specifically, cases in which the image and text are not directly connected but are associated through underlying semantic links. Moreover, noise in the evidence further impairs detection accuracy.To address these challenges, we propose CMIE, a novel OOC misinformation detection framework that incorporates a Coexistence Relationship Generation (CRG) strategy and an Association Scoring (AS) mechanism. CMIE identifies the underlying coexistence relationships between images and text, and selectively utilizes relevant evidence to enhance misinformation detection. Experimental results demonstrate that our approach outperforms existing methods.
%R 10.18653/v1/2025.findings-acl.487
%U https://aclanthology.org/2025.findings-acl.487/
%U https://doi.org/10.18653/v1/2025.findings-acl.487
%P 9342-9354
Markdown (Informal)
[CMIE: Combining MLLM Insights with External Evidence for Explainable Out-of-Context Misinformation Detection](https://aclanthology.org/2025.findings-acl.487/) (Li et al., Findings 2025)
ACL