HalluSAE: Detecting Hallucinations in Large Language Models via Sparse Auto-Encoders
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.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
SAFE: A Sparse Autoencoder-Based Framework for Robust Query Enrichment and Hallucination Mitigation in LLMs
Despite the state-of-the-art performance of Large Language Models (LLMs), these models often suffer from hallucinations, which can undermine their performance in critical applications. In this work, we propose SAFE, a no…
HallucinationDHCP: Detecting Hallucinations by Cross-modal Attention Pattern in Large Vision-Language Models
Large vision-language models (LVLMs) have demonstrated exceptional performance on complex multimodal tasks. However, they continue to suffer from significant hallucination issues, including object, attribute, and relatio…
AttributeHallucinationLRP4RAG: Detecting Hallucinations in Retrieval-Augmented Generation via Layer-wise Relevance Propagation
Retrieval-Augmented Generation (RAG) has become a primary technique for mitigating hallucinations in large language models (LLMs). However, incomplete knowledge extraction and insufficient understanding can still mislead…
RAGRetrievalRetrieval-augmented GenerationThe HalluRAG Dataset: Detecting Closed-Domain Hallucinations in RAG Applications Using an LLM's Internal States
Detecting hallucinations in large language models (LLMs) is critical for enhancing their reliability and trustworthiness. Most research focuses on hallucinations as deviations from information seen during training. Howev…
QuantizationRAGDo I Know This Entity? Knowledge Awareness and Hallucinations in Language Models
Hallucinations in large language models are a widespread problem, yet the mechanisms behind whether models will hallucinate are poorly understood, limiting our ability to solve this problem. Using sparse autoencoders as …