HalluSAE: Detecting Hallucinations in Large Language Models via Sparse Auto-Encoders

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Boshui, Fan, Zhaoxin, Wang, Ke, Leng, Zhiying, Wu, Faguo, Zheng, Hongwei, Sun, Yifan, Wu, Wenjun
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908975022211072
author Chen, Boshui
Fan, Zhaoxin
Wang, Ke
Leng, Zhiying
Wu, Faguo
Zheng, Hongwei
Sun, Yifan
Wu, Wenjun
author_facet Chen, Boshui
Fan, Zhaoxin
Wang, Ke
Leng, Zhiying
Wu, Faguo
Zheng, Hongwei
Sun, Yifan
Wu, Wenjun
contents Large Language Models (LLMs) are powerful and widely adopted, but their practical impact is limited by the well-known hallucination phenomenon. While recent hallucination detection methods have made notable progress, we find most of them overlook the dynamic nature and underlying mechanisms of it. To address this gap, we propose HalluSAE, a phase transition-inspired framework that models hallucination as a critical shift in the model's latent dynamics. By modeling the generation process as a trajectory through a potential energy landscape, HalluSAE identifies critical transition zones and attributes factual errors to specific high-energy sparse features. Our approach consists of three stages: (1) Potential Energy Empowered Phase Zone Localization via sparse autoencoders and a geometric potential energy metric; (2) Hallucination-related Sparse Feature Attribution using contrastive logit attribution; and (3) Probing-based Causal Hallucination Detection through linear probes on disentangled features. Extensive experiments on Gemma-2-9B demonstrate that HalluSAE achieves state-of-the-art hallucination detection performance.
format Preprint
id arxiv_https___arxiv_org_abs_2604_16430
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle HalluSAE: Detecting Hallucinations in Large Language Models via Sparse Auto-Encoders
Chen, Boshui
Fan, Zhaoxin
Wang, Ke
Leng, Zhiying
Wu, Faguo
Zheng, Hongwei
Sun, Yifan
Wu, Wenjun
Computation and Language
Artificial Intelligence
Large Language Models (LLMs) are powerful and widely adopted, but their practical impact is limited by the well-known hallucination phenomenon. While recent hallucination detection methods have made notable progress, we find most of them overlook the dynamic nature and underlying mechanisms of it. To address this gap, we propose HalluSAE, a phase transition-inspired framework that models hallucination as a critical shift in the model's latent dynamics. By modeling the generation process as a trajectory through a potential energy landscape, HalluSAE identifies critical transition zones and attributes factual errors to specific high-energy sparse features. Our approach consists of three stages: (1) Potential Energy Empowered Phase Zone Localization via sparse autoencoders and a geometric potential energy metric; (2) Hallucination-related Sparse Feature Attribution using contrastive logit attribution; and (3) Probing-based Causal Hallucination Detection through linear probes on disentangled features. Extensive experiments on Gemma-2-9B demonstrate that HalluSAE achieves state-of-the-art hallucination detection performance.
title HalluSAE: Detecting Hallucinations in Large Language Models via Sparse Auto-Encoders
topic Computation and Language
Artificial Intelligence
url https://arxiv.org/abs/2604.16430