From Dispersion to Attraction: Spectral Dynamics of Hallucination Across Whisper Model Scales

arXiv:2604.08591v1 Announce Type: new
Abstract: Hallucinations in large ASR models present a critical safety risk. In this work, we propose the textit{Spectral Sensitivity Theorem}, which predicts a phase transition in deep networks from a dispersive regime (signal decay) to an attractor regime (rank-1 collapse) governed by layer-wise gain and alignment. We validate this theory by analyzing the eigenspectra of activation graphs in Whisper models (Tiny to Large-v3-Turbo) under adversarial stress. Our results confirm the theoretical prediction: intermediate models exhibit textit{Structural Disintegration} (Regime I), characterized by a $13.4%$ collapse in Cross-Attention rank. Conversely, large models enter a textit{Compression-Seeking Attractor} state (Regime II), where Self-Attention actively compresses rank ($-2.34%$) and hardens the spectral slope, decoupling the model from acoustic evidence.