Leveraging Context for Multimodal Fallacy Classification in Political Debates

Alessio Pittiglio
7/21/2025
cs.CLcs.AI

No official code found. Best implementation: nlp-unibo/multimodal-am-fallacy (5 stars, CC-BY-4.0, last commit 2025-03-04). 1 more below.

Abstract

In this paper, we present our submission to the MM-ArgFallacy2025 shared task, which aims to advance research in multimodal argument mining, focusing on logical fallacies in political debates. Our approach uses pretrained Transformer-based models and proposes several ways to leverage context. In the fallacy classification subtask, our models achieved macro F1-scores of 0.4444 (text), 0.3559 (audio), and 0.4403 (multimodal). Our multimodal model showed performance comparable to the text-only model, suggesting potential for improvements.

View on arXivView PDF

Code Implementations(2)

alessiopittiglio/mm-argfallacyCommunity100%

Official source code for the paper "Leveraging Context for Multimodal Fallacy Classification in Political Debates", accepted at the ArgMining Workshop @ ACL 2025.

31PythonMay 26, 20251 years ago
acl-2025argument-miningmultimodalnatural-language-processingnlp
nlp-unibo/multimodal-am-fallacyCommunity73%
CC-BY-4.0

Multimodal Fallacy Classification in Political Debates: Dataset and Experiments.

50Shell, PythonApr 14, 20231 years agoCC-BY-4.0
argument-miningmultimodal-deep-learningnlppolitical-debatesspeech

Similar Papers

Joint Effects of Argumentation Theory, Audio Modality and Data Enrichment on LLM-Based Fallacy Classification

84% match2025

RooseBERT: A New Deal For Political Language Modelling

79% match2025

BanglaRhet: Benchmarking Classical and Transformer Models for Rhetorical and Persuasion Detection in Bangla Political Speech

78% match2026

Analysing Personal Attacks in U.S. Presidential Debates

78% match2025

Detecting Check-Worthy Claims in Political Debates, Speeches, and Interviews Using Audio Data

78% match2023

MAFALDA: A Benchmark and Comprehensive Study of Fallacy Detection and Classification

77% match1 repo92023

Cite this paper

@article{pittiglio2025leveraging,
  title  = {Leveraging Context for Multimodal Fallacy Classification in Political Debates},
  author = {Alessio Pittiglio},
  year   = {2025},
  eprint = {2507.15641},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2507.15641v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2507.15641.svg)](https://codeofpaper.com/paper/2507.15641)

Discussion