@inproceedings{tahir-etal-2025-prompt,
title = "Prompt-Guided Augmentation and Multi-modal Fusion for Argumentative Fallacy Classification in Political Debates",
author = "Tahir, Abdullah and
Ibrar, Imaan and
Ameer, Huma and
Fatima, Mehwish and
Latif, Seemab",
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-1.38/",
doi = "10.18653/v1/2025.argmining-1.38",
pages = "381--387",
ISBN = "979-8-89176-258-9",
abstract = "Classifying argumentative fallacies in political discourse is challenging due to their subtle, persuasive nature across text and speech. In our MM-ArgFallacy Shared Task submission, Team NUST investigates uni-modal (text/audio) and multi-modal (text+audio) setups using pretrained models{---}RoBERTa for text and Whisper for audio. To tackle severe class imbalance, we introduce Prompt-Guided Few-Shot Augmentation (PG-FSA) to generate synthetic samples for underrepresented fallacies. We further propose a late fusion architecture combining linguistic and paralinguistic cues, enhanced with balancing techniques like SMOTE and Focal Loss. Our approach achieves top performance across modalities, ranking 1st in text-only and multi-modal tracks, and 3rd in audio-only, on the official leaderboard. These results underscore the effectiveness of targeted augmentation and modular fusion in multi-modal fallacy classification."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tahir-etal-2025-prompt">
<titleInfo>
<title>Prompt-Guided Augmentation and Multi-modal Fusion for Argumentative Fallacy Classification in Political Debates</title>
</titleInfo>
<name type="personal">
<namePart type="given">Abdullah</namePart>
<namePart type="family">Tahir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Imaan</namePart>
<namePart type="family">Ibrar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huma</namePart>
<namePart type="family">Ameer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mehwish</namePart>
<namePart type="family">Fatima</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Seemab</namePart>
<namePart type="family">Latif</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>Classifying argumentative fallacies in political discourse is challenging due to their subtle, persuasive nature across text and speech. In our MM-ArgFallacy Shared Task submission, Team NUST investigates uni-modal (text/audio) and multi-modal (text+audio) setups using pretrained models—RoBERTa for text and Whisper for audio. To tackle severe class imbalance, we introduce Prompt-Guided Few-Shot Augmentation (PG-FSA) to generate synthetic samples for underrepresented fallacies. We further propose a late fusion architecture combining linguistic and paralinguistic cues, enhanced with balancing techniques like SMOTE and Focal Loss. Our approach achieves top performance across modalities, ranking 1st in text-only and multi-modal tracks, and 3rd in audio-only, on the official leaderboard. These results underscore the effectiveness of targeted augmentation and modular fusion in multi-modal fallacy classification.</abstract>
<identifier type="citekey">tahir-etal-2025-prompt</identifier>
<identifier type="doi">10.18653/v1/2025.argmining-1.38</identifier>
<location>
<url>https://aclanthology.org/2025.argmining-1.38/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>381</start>
<end>387</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Prompt-Guided Augmentation and Multi-modal Fusion for Argumentative Fallacy Classification in Political Debates
%A Tahir, Abdullah
%A Ibrar, Imaan
%A Ameer, Huma
%A Fatima, Mehwish
%A Latif, Seemab
%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 tahir-etal-2025-prompt
%X Classifying argumentative fallacies in political discourse is challenging due to their subtle, persuasive nature across text and speech. In our MM-ArgFallacy Shared Task submission, Team NUST investigates uni-modal (text/audio) and multi-modal (text+audio) setups using pretrained models—RoBERTa for text and Whisper for audio. To tackle severe class imbalance, we introduce Prompt-Guided Few-Shot Augmentation (PG-FSA) to generate synthetic samples for underrepresented fallacies. We further propose a late fusion architecture combining linguistic and paralinguistic cues, enhanced with balancing techniques like SMOTE and Focal Loss. Our approach achieves top performance across modalities, ranking 1st in text-only and multi-modal tracks, and 3rd in audio-only, on the official leaderboard. These results underscore the effectiveness of targeted augmentation and modular fusion in multi-modal fallacy classification.
%R 10.18653/v1/2025.argmining-1.38
%U https://aclanthology.org/2025.argmining-1.38/
%U https://doi.org/10.18653/v1/2025.argmining-1.38
%P 381-387
Markdown (Informal)
[Prompt-Guided Augmentation and Multi-modal Fusion for Argumentative Fallacy Classification in Political Debates](https://aclanthology.org/2025.argmining-1.38/) (Tahir et al., ArgMining 2025)
ACL