paper-with-me

홈 › Papers

EigenTrack: Spectral Activation Feature Tracking for Hallucination and Out-of-Distribution Detection in LLMs and VLMs

2025-09-19 · Davide Ettori, Nastaran Darabi, Sina Tayebati, Ranganath Krishnan, Mahesh Subedar, Omesh Tickoo, Amit Ranjan Trivedi arxiv

Large language models (LLMs) offer broad utility but remain prone to hallucination and out-of-distribution (OOD) errors. We propose EigenTrack, an interpretable real-time detector that uses the spectral geometry of hidden activations, a compact global signature of model dynamics. By streaming covariance-spectrum statistics such as entropy, eigenvalue gaps, and KL divergence from random baselines into a lightweight recurrent classifier, EigenTrack tracks temporal shifts in representation structure that signal hallucination and OOD drift before surface errors appear. Unlike black- and grey-box methods, it needs only a single forward pass without resampling. Unlike existing white-box detectors, it preserves temporal context, aggregates global signals, and offers interpretable accuracy-latency trade-offs.

📄 PDF Abstract BibTeX arXiv:2509.15735

Code (0)

등록된 구현이 없습니다.

Tasks

Out-of-Distribution Detection

Similar Papers 제목 키워드 기반

Spectral Geometry for Deep Learning: Compression and Hallucination Detection via Random Matrix Theory

2026-01-24 · Davide Ettori arxiv

Large language models and deep neural networks achieve strong performance but suffer from reliability issues and high computational cost. This thesis proposes a unified framework based on spectral geometry and random mat…

Knowledge Distillation

Structure and Redundancy in Large Language Models: A Spectral Study via Random Matrix Theory

2026-02-25 · Davide Ettori arxiv

This thesis addresses two persistent and closely related challenges in modern deep learning, reliability and efficiency, through a unified framework grounded in Spectral Geometry and Random Matrix Theory (RMT). As deep n…

Knowledge Distillation

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

2026-03-31 · Ivan Viakhirev, Kirill Borodin, Grach Mkrtchian arxiv

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 d…

Spectral Guardrails for Agents in the Wild: Detecting Tool Use Hallucinations via Attention Topology

2026-02-08 · Valentin Noël arxiv

Deploying autonomous agents in the wild requires reliable safeguards against tool use failures. We propose a training free guardrail based on spectral analysis of attention topology that complements supervised approaches…

LLM Hallucination Detection: A Fast Fourier Transform Method Based on Hidden Layer Temporal Signals

2025-09-16 · Jinxin Li, Gang Tu, ShengYu Cheng, Junjie Hu 외 arxiv

Hallucination remains a critical barrier for deploying large language models (LLMs) in reliability-sensitive applications. Existing detection methods largely fall into two categories: factuality checking, which is fundam…