@inproceedings{mancini-etal-2025-overview,
title = "Overview of {MM}-{A}rg{F}allacy2025 on Multimodal Argumentative Fallacy Detection and Classification in Political Debates",
author = "Mancini, Eleonora and
Ruggeri, Federico and
Villata, Serena and
Torroni, Paolo",
editor = "Chistova, Elena and
Cimiano, Philipp and
Haddadan, Shohreh and
Lapesa, Gabriella and
Ruiz-Dolz, Ramon",
booktitle = "Proceedings of the 12th Argument mining Workshop",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.argmining-1.35/",
doi = "10.18653/v1/2025.argmining-1.35",
pages = "358--368",
ISBN = "979-8-89176-258-9",
abstract = "We present an overview of the MM-ArgFallacy2025 shared task on Multimodal Argumentative Fallacy Detection and Classification in Political Debates, co-located with the 12th Workshop on Argument Mining at ACL 2025. The task focuses on identifying and classifying argumentative fallacies across three input modes: text-only, audio-only, and multimodal (text+audio), offering both binary detection (AFD) and multi-class classification (AFC) subtasks. The dataset comprises 18,925 instances for AFD and 3,388 instances for AFC, from the MM-USED-Fallacy corpus on U.S. presidential debates, annotated for six fallacy types: Ad Hominem, Appeal to Authority, Appeal to Emotion, False Cause, Slippery Slope, and Slogan. A total of 5 teams participated: 3 on classification and 2 on detection. Participants employed transformer-based models, particularly RoBERTa variants, with strategies including prompt-guided data augmentation, context integration, specialised loss functions, and various fusion techniques. Audio processing ranged from MFCC features to state-of-the-art speech models. Results demonstrated textual modality dominance, with best text-only performance reaching 0.4856 F1-score for classification and 0.34 for detection. Audio-only approaches underperformed relative to text but showed improvements over previous work, while multimodal fusion showed limited improvements. This task establishes important baselines for multimodal fallacy analysis in political discourse, contributing to computational argumentation and misinformation detection capabilities."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mancini-etal-2025-overview">
<titleInfo>
<title>Overview of MM-ArgFallacy2025 on Multimodal Argumentative Fallacy Detection and Classification in Political Debates</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eleonora</namePart>
<namePart type="family">Mancini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Federico</namePart>
<namePart type="family">Ruggeri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Serena</namePart>
<namePart type="family">Villata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paolo</namePart>
<namePart type="family">Torroni</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>Proceedings of the 12th Argument mining Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Chistova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philipp</namePart>
<namePart type="family">Cimiano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shohreh</namePart>
<namePart type="family">Haddadan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gabriella</namePart>
<namePart type="family">Lapesa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ramon</namePart>
<namePart type="family">Ruiz-Dolz</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">979-8-89176-258-9</identifier>
</relatedItem>
<abstract>We present an overview of the MM-ArgFallacy2025 shared task on Multimodal Argumentative Fallacy Detection and Classification in Political Debates, co-located with the 12th Workshop on Argument Mining at ACL 2025. The task focuses on identifying and classifying argumentative fallacies across three input modes: text-only, audio-only, and multimodal (text+audio), offering both binary detection (AFD) and multi-class classification (AFC) subtasks. The dataset comprises 18,925 instances for AFD and 3,388 instances for AFC, from the MM-USED-Fallacy corpus on U.S. presidential debates, annotated for six fallacy types: Ad Hominem, Appeal to Authority, Appeal to Emotion, False Cause, Slippery Slope, and Slogan. A total of 5 teams participated: 3 on classification and 2 on detection. Participants employed transformer-based models, particularly RoBERTa variants, with strategies including prompt-guided data augmentation, context integration, specialised loss functions, and various fusion techniques. Audio processing ranged from MFCC features to state-of-the-art speech models. Results demonstrated textual modality dominance, with best text-only performance reaching 0.4856 F1-score for classification and 0.34 for detection. Audio-only approaches underperformed relative to text but showed improvements over previous work, while multimodal fusion showed limited improvements. This task establishes important baselines for multimodal fallacy analysis in political discourse, contributing to computational argumentation and misinformation detection capabilities.</abstract>
<identifier type="citekey">mancini-etal-2025-overview</identifier>
<identifier type="doi">10.18653/v1/2025.argmining-1.35</identifier>
<location>
<url>https://aclanthology.org/2025.argmining-1.35/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>358</start>
<end>368</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Overview of MM-ArgFallacy2025 on Multimodal Argumentative Fallacy Detection and Classification in Political Debates
%A Mancini, Eleonora
%A Ruggeri, Federico
%A Villata, Serena
%A Torroni, Paolo
%Y Chistova, Elena
%Y Cimiano, Philipp
%Y Haddadan, Shohreh
%Y Lapesa, Gabriella
%Y Ruiz-Dolz, Ramon
%S Proceedings of the 12th Argument mining Workshop
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-258-9
%F mancini-etal-2025-overview
%X We present an overview of the MM-ArgFallacy2025 shared task on Multimodal Argumentative Fallacy Detection and Classification in Political Debates, co-located with the 12th Workshop on Argument Mining at ACL 2025. The task focuses on identifying and classifying argumentative fallacies across three input modes: text-only, audio-only, and multimodal (text+audio), offering both binary detection (AFD) and multi-class classification (AFC) subtasks. The dataset comprises 18,925 instances for AFD and 3,388 instances for AFC, from the MM-USED-Fallacy corpus on U.S. presidential debates, annotated for six fallacy types: Ad Hominem, Appeal to Authority, Appeal to Emotion, False Cause, Slippery Slope, and Slogan. A total of 5 teams participated: 3 on classification and 2 on detection. Participants employed transformer-based models, particularly RoBERTa variants, with strategies including prompt-guided data augmentation, context integration, specialised loss functions, and various fusion techniques. Audio processing ranged from MFCC features to state-of-the-art speech models. Results demonstrated textual modality dominance, with best text-only performance reaching 0.4856 F1-score for classification and 0.34 for detection. Audio-only approaches underperformed relative to text but showed improvements over previous work, while multimodal fusion showed limited improvements. This task establishes important baselines for multimodal fallacy analysis in political discourse, contributing to computational argumentation and misinformation detection capabilities.
%R 10.18653/v1/2025.argmining-1.35
%U https://aclanthology.org/2025.argmining-1.35/
%U https://doi.org/10.18653/v1/2025.argmining-1.35
%P 358-368
Markdown (Informal)
[Overview of MM-ArgFallacy2025 on Multimodal Argumentative Fallacy Detection and Classification in Political Debates](https://aclanthology.org/2025.argmining-1.35/) (Mancini et al., ArgMining 2025)
ACL