Leveraging Context for Multimodal Fallacy Classification in Political Debates

TL;DR

This paper introduces a multimodal approach using pretrained Transformer models to classify logical fallacies in political debates, leveraging context to improve argument mining, with promising results in a shared task setting.

Contribution

It proposes methods to incorporate context in multimodal argument mining and demonstrates competitive performance in fallacy classification using text, audio, and combined modalities.

Findings

Multimodal model achieved macro F1 of 0.4403

Text-only model achieved macro F1 of 0.4444

Audio modality alone had lower performance

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.