Leveraging Context for Multimodal Fallacy Classification in Political Debates
Alessio Pittiglio
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.
Related Papers
ELLIS Alicante at CQs-Gen 2025: Winning the critical thinking questions shared task: LLM-based question generation and selection2025-06-17LLMs for Argument Mining: Detection, Extraction, and Relationship Classification of pre-defined Arguments in Online Comments2025-05-29Are Large Language Models Good at Detecting Propaganda?2025-05-19Towards Comprehensive Argument Analysis in Education: Dataset, Tasks, and Method2025-05-17Exploring new Approaches for Information Retrieval through Natural Language Processing2025-05-04SLURG: Investigating the Feasibility of Generating Synthetic Online Fallacious Discourse2025-04-16Socrates or Smartypants: Testing Logic Reasoning Capabilities of Large Language Models with Logic Programming-based Test Oracles2025-04-09Large Language Models Are Better Logical Fallacy Reasoners with Counterargument, Explanation, and Goal-Aware Prompt Formulation2025-03-30