AI RESEARCH
SARA: Stress Test Reasoning in Audio Deepfake Detection
arXiv CS.CL
•
ArXi:2601.03615v2 Announce Type: replace Audio Language Models (ALMs) offer a promising shift towards explainable audio deepfake detections (ADD), moving beyond \textit{black-box} classifiers by providing transparency to their predictions via reasoning traces. However, such reasoning may not the model predictions, reflecting poor coherence, or, worse, may rationalize incorrect predictions with plausible but misleading explanation.