Knowing without Acting: The Disentangled Geometry of Safety Mechanisms in Large Language Models

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Wu, Jinman, Xie, Yi, Lin, Shen, Zhao, Shiqian, Chen, Xiaofeng
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915858489540608
author Wu, Jinman
Xie, Yi
Lin, Shen
Zhao, Shiqian
Chen, Xiaofeng
author_facet Wu, Jinman
Xie, Yi
Lin, Shen
Zhao, Shiqian
Chen, Xiaofeng
contents Safety alignment is often conceptualized as a monolithic process wherein harmfulness detection automatically triggers refusal. However, the persistence of jailbreak attacks suggests a fundamental mechanistic decoupling. We propose the \textbf{\underline{D}}isentangled \textbf{\underline{S}}afety \textbf{\underline{H}}ypothesis \textbf{(DSH)}, positing that safety computation operates on two distinct subspaces: a \textit{Recognition Axis} ($\mathbf{v}_H$, ``Knowing'') and an \textit{Execution Axis} ($\mathbf{v}_R$, ``Acting''). Our geometric analysis reveals a universal ``Reflex-to-Dissociation'' evolution, where these signals transition from antagonistic entanglement in early layers to structural independence in deep layers. To validate this, we introduce \textit{Double-Difference Extraction} and \textit{Adaptive Causal Steering}. Using our curated \textsc{AmbiguityBench}, we demonstrate a causal double dissociation, effectively creating a state of ``Knowing without Acting.'' Crucially, we leverage this disentanglement to propose the \textbf{Refusal Erasure Attack (REA)}, which achieves State-of-the-Art attack success rates by surgically lobotomizing the refusal mechanism. Furthermore, we uncover a critical architectural divergence, contrasting the \textit{Explicit Semantic Control} of Llama3.1 with the \textit{Latent Distributed Control} of Qwen2.5. The code and dataset are available at https://anonymous.4open.science/r/DSH.
format Preprint
id arxiv_https___arxiv_org_abs_2603_05773
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Knowing without Acting: The Disentangled Geometry of Safety Mechanisms in Large Language Models
Wu, Jinman
Xie, Yi
Lin, Shen
Zhao, Shiqian
Chen, Xiaofeng
Cryptography and Security
Artificial Intelligence
Machine Learning
Safety alignment is often conceptualized as a monolithic process wherein harmfulness detection automatically triggers refusal. However, the persistence of jailbreak attacks suggests a fundamental mechanistic decoupling. We propose the \textbf{\underline{D}}isentangled \textbf{\underline{S}}afety \textbf{\underline{H}}ypothesis \textbf{(DSH)}, positing that safety computation operates on two distinct subspaces: a \textit{Recognition Axis} ($\mathbf{v}_H$, ``Knowing'') and an \textit{Execution Axis} ($\mathbf{v}_R$, ``Acting''). Our geometric analysis reveals a universal ``Reflex-to-Dissociation'' evolution, where these signals transition from antagonistic entanglement in early layers to structural independence in deep layers. To validate this, we introduce \textit{Double-Difference Extraction} and \textit{Adaptive Causal Steering}. Using our curated \textsc{AmbiguityBench}, we demonstrate a causal double dissociation, effectively creating a state of ``Knowing without Acting.'' Crucially, we leverage this disentanglement to propose the \textbf{Refusal Erasure Attack (REA)}, which achieves State-of-the-Art attack success rates by surgically lobotomizing the refusal mechanism. Furthermore, we uncover a critical architectural divergence, contrasting the \textit{Explicit Semantic Control} of Llama3.1 with the \textit{Latent Distributed Control} of Qwen2.5. The code and dataset are available at https://anonymous.4open.science/r/DSH.
title Knowing without Acting: The Disentangled Geometry of Safety Mechanisms in Large Language Models
topic Cryptography and Security
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2603.05773