@inproceedings{wang-etal-2026-cil,
title = "{CIL}: Causal-Intervention and {LLM}-Synergized Multimodal Fake News Detection",
author = "Wang, Hongjie and
Chen, Hongyu and
Jiang, Peilin",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {IJCNLP}-{AACL} 2026",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-aacl.23/",
pages = "405--414",
ISBN = "979-8-89176-444-6",
abstract = "Multimodal fake news detection requires models to reason over both textual and visual evidence while remaining robust to distribution shifts in social media graphs. Existing approaches often concatenate modality-specific representations or rely on post-hoc fusion, which can leave image and text features in misaligned semantic spaces. Graph-based methods further introduce structural bias: node popularity, degree, or connectivity may become shortcut signals that correlate with labels in the training distribution but do not causally determine veracity. We present CIL, a causal-intervention and LLM-synergized framework for multimodal fake news detection. CIL first uses CLIP to obtain aligned image and text representations and constructs a multi-view semantic graph from cross-modal, intra-modal, and fused similarities. It then uses a large language model to produce high-confidence pseudo labels, which are injected as weak supervisory anchors. Finally, CIL mitigates degree-induced structural confounding with inverse propensity weighting and enforces counterfactual consistency under edge-drop interventions. Experiments on Twitter, PHEME, and Weibo suggest that each component contributes to performance, with the largest gains coming from aligned multimodal representations and causal debiasing."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2026-cil">
<titleInfo>
<title>CIL: Causal-Intervention and LLM-Synergized Multimodal Fake News Detection</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hongjie</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongyu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Peilin</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-444-6</identifier>
</relatedItem>
<abstract>Multimodal fake news detection requires models to reason over both textual and visual evidence while remaining robust to distribution shifts in social media graphs. Existing approaches often concatenate modality-specific representations or rely on post-hoc fusion, which can leave image and text features in misaligned semantic spaces. Graph-based methods further introduce structural bias: node popularity, degree, or connectivity may become shortcut signals that correlate with labels in the training distribution but do not causally determine veracity. We present CIL, a causal-intervention and LLM-synergized framework for multimodal fake news detection. CIL first uses CLIP to obtain aligned image and text representations and constructs a multi-view semantic graph from cross-modal, intra-modal, and fused similarities. It then uses a large language model to produce high-confidence pseudo labels, which are injected as weak supervisory anchors. Finally, CIL mitigates degree-induced structural confounding with inverse propensity weighting and enforces counterfactual consistency under edge-drop interventions. Experiments on Twitter, PHEME, and Weibo suggest that each component contributes to performance, with the largest gains coming from aligned multimodal representations and causal debiasing.</abstract>
<identifier type="citekey">wang-etal-2026-cil</identifier>
<location>
<url>https://aclanthology.org/2026.findings-aacl.23/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>405</start>
<end>414</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CIL: Causal-Intervention and LLM-Synergized Multimodal Fake News Detection
%A Wang, Hongjie
%A Chen, Hongyu
%A Jiang, Peilin
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Findings of the Association for Computational Linguistics: IJCNLP-AACL 2026
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-444-6
%F wang-etal-2026-cil
%X Multimodal fake news detection requires models to reason over both textual and visual evidence while remaining robust to distribution shifts in social media graphs. Existing approaches often concatenate modality-specific representations or rely on post-hoc fusion, which can leave image and text features in misaligned semantic spaces. Graph-based methods further introduce structural bias: node popularity, degree, or connectivity may become shortcut signals that correlate with labels in the training distribution but do not causally determine veracity. We present CIL, a causal-intervention and LLM-synergized framework for multimodal fake news detection. CIL first uses CLIP to obtain aligned image and text representations and constructs a multi-view semantic graph from cross-modal, intra-modal, and fused similarities. It then uses a large language model to produce high-confidence pseudo labels, which are injected as weak supervisory anchors. Finally, CIL mitigates degree-induced structural confounding with inverse propensity weighting and enforces counterfactual consistency under edge-drop interventions. Experiments on Twitter, PHEME, and Weibo suggest that each component contributes to performance, with the largest gains coming from aligned multimodal representations and causal debiasing.
%U https://aclanthology.org/2026.findings-aacl.23/
%P 405-414
Markdown (Informal)
[CIL: Causal-Intervention and LLM-Synergized Multimodal Fake News Detection](https://aclanthology.org/2026.findings-aacl.23/) (Wang et al., Findings 2026)
ACL