Imagen de Portada

Towards Steering without Sacrifice: Principled Training of Steering Vectors for Prompt-only Interventions

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Bao, Yuntai, Li, Qinfeng, Yu, Xinyan, Zhang, Xuhong, Su, Ge, Zhang, Wenqi, Yan, Liu, Weng, Haiqin, Yin, Jianwei
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Faithful Bi-Directional Model Steering via Distribution Matching and Distributed Interchange Interventions
por: Bao, Yuntai, et al.
Publicado: (2026)

PragLocker: Protecting Agent Intellectual Property in Untrusted Deployments via Non-Portable Prompts
por: Li, Qinfeng, et al.
Publicado: (2026)

Beyond Steering Vector: Flow-based Activation Steering for Inference-Time Intervention
por: Jin, Zehao, et al.
Publicado: (2026)

Scalable Multi-Stage Influence Function for Large Language Models via Eigenvalue-Corrected Kronecker-Factored Parameterization
por: Bao, Yuntai, et al.
Publicado: (2025)

Probing the Geometry of Truth: Consistency and Generalization of Truth Directions in LLMs Across Logical Transformations and Question Answering Tasks
por: Bao, Yuntai, et al.
Publicado: (2025)

Steer2Edit: From Activation Steering to Component-Level Editing
por: Sun, Chung-En, et al.
Publicado: (2026)

Global Evolutionary Steering: Refining Activation Steering Control via Cross-Layer Consistency
por: Jiang, Xinyan, et al.
Publicado: (2026)

EasySteer: A Unified Framework for High-Performance and Extensible LLM Steering
por: Xu, Haolei, et al.
Publicado: (2025)

Personalized Steering of Large Language Models: Versatile Steering Vectors Through Bi-directional Preference Optimization
por: Cao, Yuanpu, et al.
Publicado: (2024)

AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint
por: Sheng, Leheng, et al.
Publicado: (2025)

Steer Like the LLM: Activation Steering that Mimics Prompting
por: Heyman, Geert, et al.
Publicado: (2026)

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

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

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

Persona Vectors in Games: Measuring and Steering Strategies via Activation Vectors
por: Sun, Johnathan, et al.
Publicado: (2026)

No Training Wheels: Steering Vectors for Bias Correction at Inference Time
por: Gupta, Aviral, et al.
Publicado: (2025)

HijackRAG: Hijacking Attacks against Retrieval-Augmented Large Language Models
por: Zhang, Yucheng, et al.
Publicado: (2024)

VSPO: Vector-Steered Policy Optimization for Behavioral Control
por: Zhang, Xuechen, et al.
Publicado: (2026)

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

TransLinkGuard: Safeguarding Transformer Models Against Model Stealing in Edge Deployment
por: Li, Qinfeng, et al.
Publicado: (2024)

FineSteer: A Unified Framework for Fine-Grained Inference-Time Steering in Large Language Models
por: Weng, Zixuan, et al.
Publicado: (2026)

Subliminal Learning Is Steering Vector Distillation
por: Blank, Camila, et al.
Publicado: (2026)

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

Analyzing the Generalization and Reliability of Steering Vectors
por: Tan, Daniel, et al.
Publicado: (2024)

Predicting Where Steering Vectors Succeed
por: Billa, Jayadev
Publicado: (2026)

Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions
por: Kang, Diancheng, et al.
Publicado: (2026)

Steering-induced phase transition in measurement-only quantum circuits
por: Qian, Dongheng, et al.
Publicado: (2023)

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

Spectral Attention Steering for Prompt Highlighting
por: Li, Weixian Waylon, et al.
Publicado: (2026)

White-Box Sensitivity Auditing with Steering Vectors
por: Cyberey, Hannah, et al.
Publicado: (2026)

Dialz: A Python Toolkit for Steering Vectors
por: Siddique, Zara, et al.
Publicado: (2025)

CogSteer: Cognition-Inspired Selective Layer Intervention for Efficiently Steering Large Language Models
por: Wang, Xintong, et al.
Publicado: (2024)

PrimeComposer: Faster Progressively Combined Diffusion for Image Composition with Attention Steering
por: Wang, Yibin, et al.
Publicado: (2024)

Neural Quantum States in Variational Monte Carlo Method: A Brief Summary
por: Song, Yuntai
Publicado: (2024)

Adaptive Multi-Subspace Representation Steering for Attribute Alignment in Large Language Models
por: Jiang, Xinyan, et al.
Publicado: (2025)

MedSteer: Counterfactual Endoscopic Synthesis via Training-Free Activation Steering
por: Pham, Trong-Thang, et al.
Publicado: (2026)

Where to Steer: Input-Dependent Layer Selection for Steering Improves LLM Alignment
por: Gadgil, Soham, et al.
Publicado: (2026)

ROAST: Rollout-based On-distribution Activation Steering Technique
por: Su, Xuanbo, et al.
Publicado: (2026)

Towards Understanding Steering Strength
por: Taimeskhanov, Magamed, et al.
Publicado: (2026)

Causal Interventions on Continuous Variables: A Case Study on Verb Bias in Steering Vectors for In-Context Learning
por: Zhou, Zhenghao Herbert, et al.
Publicado: (2026)