Leveraging Context for Multimodal Fallacy Classification in Political Debates

2025/07/21 by Pittiglio, Alessio · 1 citation
#Artificial Intelligence (cs.AI) #Computation and Language (cs.CL) #FOS: Computer and information sciences

paper · doi:10.48550/arxiv.2507.15641

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.

Citations

• FlashAttention-2: Faster Attention with Better Parallelism and Work Partitioning
• DeBERTaV3: Improving DeBERTa using ELECTRA-Style Pre-Training with Gradient-Disentangled Embedding Sharing
• WavLM: Large-Scale Self-Supervised Pre-Training for Full Stack Speech Processing
• HuBERT: Self-Supervised Speech Representation Learning by Masked\n Prediction of Hidden Units
• wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations
• Longformer: The Long-Document Transformer
• Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks
• RoBERTa: A Robustly Optimized BERT Pretraining Approach
• Practical Bayesian Optimization of Machine Learning Algorithms
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Cited by

• A Simple Method to Enhance Pre-trained Language Models with Speech Tokens for Classification

Related

• Joint Effects of Argumentation Theory, Audio Modality and Data Enrichment on LLM-Based Fallacy Classification
• RooseBERT: A New Deal For Political Language Modelling
• Limited Generalizability in Argument Mining: State-Of-The-Art Models Learn Datasets, Not Arguments
• M2P2: Multimodal Persuasion Prediction using Adaptive Fusion
• DebateSum: A large-scale argument mining and summarization dataset