Multimodal Argument Mining

MM-ArgFallacy2025 benchmarks fallacy detection and classification in U.S. presidential debates from text, audio, or both, and finds that text-based systems still score highest.

Releases the first corpus pairing political debate text with audio for classifying six fallacy types, and shows that adding audio improves classification for several models.

MM-USElecDeb60To16 aligns decades of US presidential debate transcripts with their audio, and shows that pre-trained audio embeddings beat spectral features for argument mining.