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

arXiv: https://arxiv.org/abs/2509.15735 · HTML: https://mlsanity.com/paper/2509.15735/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 30 references that are in the map.
- First posted on arXiv 19 Sep 2025.

## Builds on (most cited first, 19 of 19)

- [A Baseline for Detecting Misclassified and Out-of-Distribution Examples in Neural Networks](https://mlsanity.com/paper/1610.02136/) (2016)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [DetectGPT: Zero-Shot Machine-Generated Text Detection using Probability Curvature](https://mlsanity.com/paper/2301.11305/) (2023)
- [Fast-DetectGPT: Efficient Zero-Shot Detection of Machine-Generated Text via Conditional Probability Curvature](https://mlsanity.com/paper/2310.05130/) (2023)
- [Implicit Self-Regularization in Deep Neural Networks: Evidence from Random Matrix Theory and Implications for Learning](https://mlsanity.com/paper/1810.01075/) (2018)
- [ReDeEP: Detecting Hallucination in Retrieval-Augmented Generation via Mechanistic Interpretability](https://mlsanity.com/paper/2410.11414/) (2024)
- [Unsupervised Real-Time Hallucination Detection based on the Internal States of Large Language Models](https://mlsanity.com/paper/2403.06448/) (2024)
- [How Does BERT Answer Questions? A Layer-Wise Analysis of Transformer Representations](https://mlsanity.com/paper/1909.04925/) (2019)
- [RankFeat: Rank-1 Feature Removal for Out-of-distribution Detection](https://mlsanity.com/paper/2209.08590/) (2022)
- [Hallucination Detection in LLMs Using Spectral Features of Attention Maps](https://mlsanity.com/paper/2502.17598/) (2025)
- [Chain of Natural Language Inference for Reducing Large Language Model Ungrounded Hallucinations](https://mlsanity.com/paper/2310.03951/) (2023)
- [Weight decay induces low-rank attention layers](https://mlsanity.com/paper/2410.23819/) (2024)
- [Cost-Effective Hallucination Detection for LLMs](https://mlsanity.com/paper/2407.21424/) (2024)
- [Glimpse: Enabling White-Box Methods to Use Proprietary Models for Zero-Shot LLM-Generated Text Detection](https://mlsanity.com/paper/2412.11506/) (2024)
- [Lightweight, Uncertainty-Aware Conformalized Visual Odometry](https://mlsanity.com/paper/2303.02207/) (2023)
- [Mutual Information-calibrated Conformal Feature Fusion for Uncertainty-Aware Multimodal 3D Object Detection at the Edge](https://mlsanity.com/paper/2309.09593/) (2023)
- [SPARC: Subspace-Aware Prompt Adaptation for Robust Continual Learning in LLMs](https://mlsanity.com/paper/2502.02909/) (2025)
- [EigenShield: Causal Subspace Filtering via Random Matrix Theory for Adversarially Robust Vision-Language Models](https://mlsanity.com/paper/2502.14976/) (2025)
- [SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps](https://mlsanity.com/paper/2505.15177/) (2025)

## Built on by (most cited first, 10 of 10)

- [Improving Semantic Uncertainty Quantification in LVLMs with Semantic Gaussian Processes](https://mlsanity.com/paper/2512.14177/) (2025)
- [Algebraic Dead Directions in LayerNorm Transformers: A Forward-Pass-Only Diagnostic at LLM Scale](https://mlsanity.com/paper/2606.19491/) (2026)
- [Dead-Direction Signatures: A Cheap Spectral Reading of Singular Complexity](https://mlsanity.com/paper/2606.21158/) (2026)
- [Does Bielik Know What It Doesn't Know? Activation Dispersion Separates Entity Familiarity from Factual Reliability Across Model Scale](https://mlsanity.com/paper/2607.07670/) (2026)
- [When Context Bites: Detecting RAG Poisoning via Document-Level Attention Collapse](https://mlsanity.com/paper/2608.06947/) (2026)
- [Spectral Archaeology: The Causal Topology of Model Evolution](https://mlsanity.com/paper/2601.03424/) (2026)
- [Self-Attention as Transport: Limits of Symmetric Spectral Diagnostics](https://mlsanity.com/paper/2605.04893/) (2026)
- [Leveraging Visual Signals for Robust Token-Level Uncertainty in Vision-Language Generation](https://mlsanity.com/paper/2605.27136/) (2026)
- [Graded Entity-Familiarity Readouts in Language Models: Polish Adaptation, Cross-Language Robustness, and Refusal Steering](https://mlsanity.com/paper/2607.13568/) (2026)
- [Prediction of Prediction (PoP): Inter-Layer Activation Fusion for Single-Pass Hallucination Detection in Large Language Models](https://mlsanity.com/paper/2608.27165/) (2026)

## Abstract (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.