Cover Image

SteeringSafety: A Systematic Safety Evaluation Framework of Representation Steering in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Siu, Vincent, Crispino, Nicholas, Park, David, Henry, Nathan W., Wang, Zhun, Liu, Yang, Song, Dawn, Wang, Chenguang
Format:	Preprint
Published:	2025
Subjects:	Artificial Intelligence Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

RepIt: Steering Language Models with Concept-Specific Refusal Vectors
by: Siu, Vincent, et al.
Published: (2025)

COSMIC: Generalized Refusal Direction Identification in LLM Activations
by: Siu, Vincent, et al.
Published: (2025)

Peer-Preservation in Frontier Models
by: Potter, Yujin, et al.
Published: (2026)

Agent Instructs Large Language Models to be General Zero-Shot Reasoners
by: Crispino, Nicholas, et al.
Published: (2023)

SafeSteer: Localized On-Policy Distillation for Efficient Safety Alignment
by: Li, Hao, et al.
Published: (2026)

Analysing the Safety Pitfalls of Steering Vectors
by: Li, Yuxiao, et al.
Published: (2026)

Gradient-Controlled Decoding: A Safety Guardrail for LLMs with Dual-Anchor Steering
by: Chiniya, Purva, et al.
Published: (2026)

Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations
by: Hazra, Rima, et al.
Published: (2024)

Investigating Bias Representations in Llama 2 Chat via Activation Steering
by: Lu, Dawn, et al.
Published: (2024)

Steering Over-refusals Towards Safety in Retrieval Augmented Generation
by: Maskey, Utsav, et al.
Published: (2025)

The Cylindrical Representation Hypothesis for Language Model Steering
by: Gao, Lang, et al.
Published: (2026)

SteerConf: Steering LLMs for Confidence Elicitation
by: Zhou, Ziang, et al.
Published: (2025)

Steering LLMs for Culturally Localized Generation
by: Khanuja, Simran, et al.
Published: (2026)

A Framework for Formalizing LLM Agent Security
by: Siu, Vincent, et al.
Published: (2026)

FairSteer: Inference Time Debiasing for LLMs with Dynamic Activation Steering
by: Li, Yichen, et al.
Published: (2025)

Steering Multimodal Large Language Models Decoding for Context-Aware Safety
by: Liu, Zheyuan, et al.
Published: (2025)

Towards Reliable Evaluation of Behavior Steering Interventions in LLMs
by: Pres, Itamar, et al.
Published: (2024)

Psychological Steering in LLMs: An Evaluation of Effectiveness and Trustworthiness
by: Banayeeanzade, Amin, et al.
Published: (2025)

SafeSteer: Interpretable Safety Steering with Refusal-Evasion in LLMs
by: Ghosh, Shaona, et al.
Published: (2025)

Steering Knowledge Selection Behaviours in LLMs via SAE-Based Representation Engineering
by: Zhao, Yu, et al.
Published: (2024)

Soteria: Language-Specific Functional Parameter Steering for Multilingual Safety Alignment
by: Banerjee, Somnath, et al.
Published: (2025)

Steering LLMs toward Korean Local Speech: Iterative Refinement Framework for Faithful Dialect Translation
by: Park, Keunhyeung, et al.
Published: (2025)

Semantics-Adaptive Activation Intervention for LLMs via Dynamic Steering Vectors
by: Wang, Weixuan, et al.
Published: (2024)

Improving Steering Vectors by Targeting Sparse Autoencoder Features
by: Chalnev, Sviatoslav, et al.
Published: (2024)

Exploring the Personality Traits of LLMs through Latent Features Steering
by: Yang, Shu, et al.
Published: (2024)

UniMaia: Steering Chess Policies with Language for Human-like Play
by: Siu, Sherman, et al.
Published: (2026)

Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs
by: Han, Pengrui, et al.
Published: (2026)

Continuously Steering LLMs Sensitivity to Contextual Knowledge with Proxy Models
by: Wang, Yilin, et al.
Published: (2025)

Analyzing Finetuning Representation Shift for Multimodal LLMs Steering
by: Khayatan, Pegah, et al.
Published: (2025)

ExpertSteer: Intervening in LLMs through Expert Knowledge
by: Wang, Weixuan, et al.
Published: (2025)

Activation Steering for Synthetic Data Generation: The Role of Diversity in Downstream Safety Detection
by: Deshpande, Vijeta, et al.
Published: (2026)

Towards Inference-time Category-wise Safety Steering for Large Language Models
by: Bhattacharjee, Amrita, et al.
Published: (2024)

Learning to Steer: Input-dependent Steering for Multimodal LLMs
by: Parekh, Jayneel, et al.
Published: (2025)

Trojan Activation Attack: Red-Teaming Large Language Models using Activation Steering for Safety-Alignment
by: Wang, Haoran, et al.
Published: (2023)

A Systematic Analysis of the Impact of Persona Steering on LLM Capabilities
by: Chen, Jiaqi, et al.
Published: (2026)

SteerX: Disentangled Steering for LLM Personalization
by: Zhao, Xiaoyan, et al.
Published: (2025)

Improved Representation Steering for Language Models
by: Wu, Zhengxuan, et al.
Published: (2025)

Multimodal Situational Safety
by: Zhou, Kaiwen, et al.
Published: (2024)

Steering Awareness: Detecting Activation Steering from Within
by: Rivera, Joshua Fonseca, et al.
Published: (2025)

LLM CHESS: Benchmarking Reasoning and Instruction-Following in LLMs through Chess
by: Kolasani, Sai, et al.
Published: (2025)