通过融合多模态上下文，提升政治辩论中逻辑谬误的识别能力。
Leveraging Context for Multimodal Fallacy Classification in Political Debates
- 利用预训练Transformer模型融合文本、音频与多模态上下文。
- 多模态模型取得0.4403的宏平均F1，接近纯文本模型表现。
- 适合关注政治辩论分析与多模态推理的研究者。
本文提交至MM-ArgFallacy2025共享任务，旨在推动多模态论证挖掘研究，聚焦政治辩论中的逻辑谬误识别。我们采用基于预训练Transformer的模型，并提出多种上下文利用策略。在谬误分类任务中，模型在文本、音频和多模态上的宏平均F1得分分别为0.4444、0.3559和0.4403。多模态模型性能与纯文本模型相当，表明其具备进一步优化潜力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。