Cover Image

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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Viakhirev, Ivan, Borodin, Kirill, Mkrtchian, Grach
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Interpreting Multi-Branch Anti-Spoofing Architectures: Correlating Internal Strategy with Empirical Performance
by: Viakhirev, Ivan, et al.
Published: (2026)

Evaluating Generalization and Robustness in Russian Anti-Spoofing: The RuASD Initiative
by: Lysikova, Ksenia, et al.
Published: (2026)

Benchmarking Compact VLMs for Clip-Level Surveillance Anomaly Detection Under Weak Supervision
by: Borodin, Kirill, et al.
Published: (2026)

Application of ASV for Voice Identification after VC and Duration Predictor Improvement in TTS Models
by: Nikolayevich, Borodin Kirill, et al.
Published: (2024)

AASIST3: KAN-Enhanced AASIST Speech Deepfake Detection using SSL Features and Additional Regularization for the ASVspoof 2024 Challenge
by: Borodin, Kirill, et al.
Published: (2024)

When Spoof Detectors Travel: Evaluation Across 66 Languages in the Low-Resource Language Spoofing Corpus
by: Borodin, Kirill, et al.
Published: (2026)

Spectral Edge Dynamics of Training Trajectories: Signal--Noise Geometry Across Scales
by: Xu, Yongzhong
Published: (2026)

From Visual to Multimodal: Systematic Ablation of Encoders and Fusion Strategies in Animal Identification
by: Kudryavtsev, Vasiliy, et al.
Published: (2026)

Concepts Whisper While Syntax Shouts: Spectral Anti-Concentration and the Dual Geometry of Transformer Representations
by: Acharya, Pratyush, et al.
Published: (2026)

Manifold of Failure: Behavioral Attraction Basins in Language Models
by: Munshi, Sarthak, et al.
Published: (2026)

Origin-Destination Demand Prediction: An Urban Radiation and Attraction Perspective
by: Ma, Xuan, et al.
Published: (2024)

Spectral Geometry for Deep Learning: Compression and Hallucination Detection via Random Matrix Theory
by: Ettori, Davide
Published: (2026)

From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers
by: Suresh, Praneet, et al.
Published: (2025)

Whispering to a Blackbox: Bootstrapping Frozen OCR with Visual Prompts
by: Samandarov, Samandar, et al.
Published: (2026)

Hallucination Detection in LLMs Using Spectral Features of Attention Maps
by: Binkowski, Jakub, et al.
Published: (2025)

Combining Masked Language Modeling and Cross-Modal Contrastive Learning for Prosody-Aware TTS
by: Borodin, Kirill, et al.
Published: (2026)

Emergent Causal-Geometric Dynamics Across Depth in Large Language Models
by: Haim, Shahar, et al.
Published: (2026)

Dynamics-inspired Structure Hallucination for Protein-protein Interaction Modeling
by: Wu, Fang, et al.
Published: (2026)

Generation Constraint Scaling Can Mitigate Hallucination
by: Kollias, Georgios, et al.
Published: (2024)

Scaling Laws Across Model Architectures: A Comparative Analysis of Dense and MoE Models in Large Language Models
by: Wang, Siqi, et al.
Published: (2024)

Attention Dispersion in Dynamic Graph Transformers: Diagnosis and a Transferable Fix
by: Zhang, Jinhao, et al.
Published: (2026)

WhisperD: Dementia Speech Recognition and Filler Word Detection with Whisper
by: Akinrintoyo, Emmanuel, et al.
Published: (2025)

Do Post-Training Algorithms Actually Differ? A Controlled Study Across Model Scales Uncovers Scale-Dependent Ranking Inversions
by: Li, Xiaoyi
Published: (2026)

Towards Scalable AASIST: Refining Graph Attention for Speech Deepfake Detection
by: Viakhirev, Ivan, et al.
Published: (2025)

Memory-Efficient LLM Training with Dynamic Sparsity: From Stability to Practical Scaling
by: Xiao, Qiao, et al.
Published: (2026)

From Flat Facts to Sharp Hallucinations: Detecting Stubborn Errors via Gradient Sensitivity
by: Liew, Yee Zhing, et al.
Published: (2026)

PSNE: Efficient Spectral Sparsification Algorithms for Scaling Network Embedding
by: Lin, Longlong, et al.
Published: (2024)

Why DDIM Hallucinates More Than DDPM: A Theoretical Analysis of Reverse Dynamics
by: Ashiq, Muhammad H., et al.
Published: (2026)

Scaling Law Phenomena Across Regression Paradigms: Multiple and Kernel Approaches
by: Chen, Yifang, et al.
Published: (2025)

Spectral Guardrails for Agents in the Wild: Detecting Tool Use Hallucinations via Attention Topology
by: Noël, Valentin
Published: (2026)

Spectral Edge Dynamics Reveal Functional Modes of Learning
by: Xu, Yongzhong
Published: (2026)

Approaching Deep Learning through the Spectral Dynamics of Weights
by: Yunis, David, et al.
Published: (2024)

Dynamic Spectral Backpropagation for Efficient Neural Network Training
by: Muthuraman, Mannmohan
Published: (2025)

Learning Robust Spectral Dynamics for Temporal Domain Generalization
by: Yu, En, et al.
Published: (2025)

When Denoising Hinders: Revisiting Zero-Shot ASR with SAM-Audio and Whisper
by: Islam, Akif, et al.
Published: (2026)

Model Mimic Attack: Knowledge Distillation for Provably Transferable Adversarial Examples
by: Lukyanov, Kirill, et al.
Published: (2024)

Mitigating Value Hallucination in Dyna Planning via Multistep Predecessor Models
by: Aminmansour, Farzane, et al.
Published: (2020)

HalluField: Detecting LLM Hallucinations via Field-Theoretic Modeling
by: Vu, Minh, et al.
Published: (2025)

No Free Lunch: Fundamental Limits of Learning Non-Hallucinating Generative Models
by: Wu, Changlong, et al.
Published: (2024)

Balalaika: Data-Centric, Prosody-Aware Annotation Pipeline for Russian Speech
by: Borodin, Kirill, et al.
Published: (2025)