From Dispersion to Attraction: Spectral Dynamics of Hallucination Across Whisper Model Scales
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
Record details
Published: 31 March 2026
Source: arXiv
Category: Research
Topics: Safety & alignment
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
The Geometry of Compromise: Unlocking Generative Capabilities via Controllable Modality Alignment
arXiv · 31 March 2026
Robust Multimodal Safety via Conditional Decoding
arXiv · 31 March 2026
The Persistent Vulnerability of Aligned AI Systems
arXiv · 31 March 2026
Diversity-Aware Reverse Kullback-Leibler Divergence for Large Language Model Distillation
arXiv · 31 March 2026
Neural-Assisted in-Motion Self-Heading Alignment
arXiv · 31 March 2026
Hierarchical Pre-Training of Vision Encoders with Large Language Models
arXiv · 31 March 2026
How to cite this record
ethics.ai (31 March 2026), “From Dispersion to Attraction: Spectral Dynamics of Hallucination Across Whisper Model Scales,” evidence record 6516, https://ethics.ai/record/6516 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.