Cover Image

From Noise to Narrative: Tracing the Origins of Hallucinations in Transformers

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Suresh, Praneet, Stanley, Jack, Joseph, Sonia, Scimeca, Luca, Bzdok, Danilo
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Quantifying LLM Attention-Head Stability: Implications for Circuit Universality
by: Bali, Karan, et al.
Published: (2026)

Steering CLIP's vision transformer with sparse autoencoders
by: Joseph, Sonia, et al.
Published: (2025)

Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video
by: Joseph, Sonia, et al.
Published: (2025)

Shaping Inductive Bias in Diffusion Models through Frequency-Based Noise Control
by: Jiralerspong, Thomas, et al.
Published: (2025)

Learning What Matters: Steering Diffusion via Spectrally Anisotropic Forward Noise
by: Scimeca, Luca, et al.
Published: (2025)

The Uncanny Valley: A Comprehensive Analysis of Diffusion Models
by: Ghanem, Karam, et al.
Published: (2024)

Scalable Ensemble Diversification for OOD Generalization and Detection
by: Rubinstein, Alexander, et al.
Published: (2024)

NoiseFormer -- Noise Diffused Symmetric Attention Transformer
by: Kumar, Phani, et al.
Published: (2026)

OT-Transformer: A Continuous-time Transformer Architecture with Optimal Transport Regularization
by: Kan, Kelvin, et al.
Published: (2025)

Mitigating Shortcut Learning with Diffusion Counterfactuals and Diverse Ensembles
by: Scimeca, Luca, et al.
Published: (2023)

Noise Stability of Transformer Models
by: Haris, Themistoklis, et al.
Published: (2026)

Estimating Unknown Population Sizes Using the Hypergeometric Distribution
by: Hodgson, Liam, et al.
Published: (2024)

Transcoders Trace Visual Grounding and Hallucinations in Vision-Language Models
by: Damianos, Dimitrios, et al.
Published: (2026)

Exploring Loss Design Techniques For Decision Tree Robustness To Label Noise
by: Sztukiewicz, Lukasz, et al.
Published: (2024)

The Map of Misbelief: Tracing Intrinsic and Extrinsic Hallucinations Through Attention Patterns
by: Hajji, Elyes, et al.
Published: (2025)

Sample Transform Cost-Based Training-Free Hallucination Detector for Large Language Models
by: Ding, Zeyang, et al.
Published: (2026)

Uncovering Graph Reasoning in Decoder-only Transformers with Circuit Tracing
by: Dai, Xinnan, et al.
Published: (2025)

Mechanistic Data Attribution: Tracing the Training Origins of Interpretable LLM Units
by: Chen, Jianhui, et al.
Published: (2026)

From Noise to Control: Parameterized Diffusion Policies
by: Zhang, Renhao, et al.
Published: (2026)

From Dispersion to Attraction: Spectral Dynamics of Hallucination Across Whisper Model Scales
by: Viakhirev, Ivan, et al.
Published: (2026)

Circuit Complexity of Hierarchical Knowledge Tracing and Implications for Log-Precision Transformers
by: Liu, Naiming, et al.
Published: (2026)

Precision Tracked Transformer via Kalman Filtering, Kriging and Process Noise
by: Long, Bo, et al.
Published: (2026)

Surgical Knowledge Rewrite in Compact LLMs: An 'Unlearn-then-Learn' Strategy with ($IA^3$) for Localized Factual Modulation and Catastrophic Forgetting Mitigation
by: Ngugi, Stanley
Published: (2025)

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

Priming: Hybrid State Space Models From Pre-trained Transformers
by: Chattopadhyay, Aditya, et al.
Published: (2026)

ThinkTank: A Framework for Generalizing Domain-Specific AI Agent Systems into Universal Collaborative Intelligence Platforms
by: Surabhi, Praneet Sai Madhu, et al.
Published: (2025)

Noise-corrected GRPO: From Noisy Rewards to Unbiased Gradients
by: Mansouri, Omar El, et al.
Published: (2025)

Navigating Shortcuts, Spurious Correlations, and Confounders: From Origins via Detection to Mitigation
by: Steinmann, David, et al.
Published: (2024)

From Simulation to Enaction: Post-trained language models recognize and react to their own generations
by: G., Asvin, et al.
Published: (2026)

Operational Wind Speed Forecasts for Chile's Electric Power Sector Using a Hybrid ML Model
by: Suri, Dhruv, et al.
Published: (2024)

STLGT: A Scalable Trace-Based Linear Graph Transformer for Tail Latency Prediction in Microservices
by: Ding, Yongliang, et al.
Published: (2026)

Versatile Cardiovascular Signal Generation with a Unified Diffusion Transformer
by: Chen, Zehua, et al.
Published: (2025)

Cisco Time Series Model Technical Report
by: Gou, Liang, et al.
Published: (2025)

Hallucination as Trajectory Commitment: Causal Evidence for Asymmetric Attractor Dynamics in Transformer Generation
by: Akarlar, G. Aytug
Published: (2026)

Prediction of Bank Credit Ratings using Heterogeneous Topological Graph Neural Networks
by: Liu, Junyi, et al.
Published: (2025)

From Noise to Precision: A Diffusion-Driven Approach to Zero-Inflated Precipitation Prediction
by: Gao, Wentao, et al.
Published: (2025)

Learning to Reason for Hallucination Span Detection
by: Su, Hsuan, et al.
Published: (2025)

Grokking as Structural Inference: Transformers Need Bayesian Lottery Tickets
by: Hidajat, Kai, et al.
Published: (2026)

Origin Tracer: A Method for Detecting LoRA Fine-Tuning Origins in LLMs
by: Liang, Hongyu, et al.
Published: (2025)

Rethinking Hallucinations: Correctness, Consistency, and Prompt Multiplicity
by: Ganesh, Prakhar, et al.
Published: (2026)