Cover Image

Where to Steer: Input-Dependent Layer Selection for Steering Improves LLM Alignment

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Gadgil, Soham, Lin, Chris, Lee, Su-In
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Ensembling Sparse Autoencoders
by: Gadgil, Soham, et al.
Published: (2025)

Estimating Conditional Mutual Information for Dynamic Feature Selection
by: Gadgil, Soham, et al.
Published: (2023)

Data Alignment for Zero-Shot Concept Generation in Dermatology AI
by: Gadgil, Soham, et al.
Published: (2024)

Selective Steering: Norm-Preserving Control Through Discriminative Layer Selection
by: Dang, Quy-Anh, et al.
Published: (2026)

SurrogateSHAP: Training-Free Contributor Attribution for Text-to-Image (T2I) Models
by: Lu, Mingyu, et al.
Published: (2026)

Can Revealed Preferences Clarify LLM Alignment and Steering?
by: Yamin, Khurram, et al.
Published: (2026)

Predicting Where Steering Vectors Succeed
by: Billa, Jayadev
Published: (2026)

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

Transformer-based Time-Series Biomarker Discovery for COPD Diagnosis
by: Gadgil, Soham, et al.
Published: (2024)

BarrierSteer: LLM Safety via Learning Barrier Steering
by: Tran, Thanh Q., et al.
Published: (2026)

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

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

Towards Steering without Sacrifice: Principled Training of Steering Vectors for Prompt-only Interventions
by: Bao, Yuntai, et al.
Published: (2026)

Steered LLM Activations are Non-Surjective
by: Mishra, Aayush, et al.
Published: (2026)

SteerVLM: Robust Model Control through Lightweight Activation Steering for Vision Language Models
by: Sivakumar, Anushka, et al.
Published: (2025)

Differentially Private Steering for Large Language Model Alignment
by: Goel, Anmol, et al.
Published: (2025)

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

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

Selective Safety Steering via Value-Filtered Decoding
by: Einbinder, Bat-Sheva, et al.
Published: (2026)

LLMSteer: Improving Long-Context LLM Inference by Steering Attention on Reused Contexts
by: Gu, Zhuohan, et al.
Published: (2024)

Tell Your Model Where to Attend: Post-hoc Attention Steering for LLMs
by: Zhang, Qingru, et al.
Published: (2023)

Classification for everyone : Building geography agnostic models for fairer recognition
by: Jindal, Akshat, et al.
Published: (2023)

Steer LLM Latents for Hallucination Detection
by: Park, Seongheon, et al.
Published: (2025)

GSS: Gated Subspace Steering for Selective Memorization Mitigation in LLMs
by: Zhang, Xuanqi, et al.
Published: (2026)

HyperSteer: Activation Steering at Scale with Hypernetworks
by: Sun, Jiuding, et al.
Published: (2025)

MidSteer: Optimal Affine Framework for Steering Generative Models
by: Gaintseva, Tatiana, et al.
Published: (2026)

To Steer or Not to Steer? Mechanistic Error Reduction with Abstention for Language Models
by: Hedström, Anna, et al.
Published: (2025)

Adaptive Probe-based Steering for Robust LLM Jailbreaking
by: Chen, Junxi, et al.
Published: (2026)

The Rogue Scalpel: Activation Steering Compromises LLM Safety
by: Korznikov, Anton, et al.
Published: (2025)

Steering LLM Reasoning Through Bias-Only Adaptation
by: Sinii, Viacheslav, et al.
Published: (2025)

Graph-Regularized Sparse Autoencoders for LLM Safety Steering
by: Yeon, Jehyeok, et al.
Published: (2025)

Understanding and Mitigating Dataset Corruption in LLM Steering
by: Anderson, Cullen, et al.
Published: (2026)

Compositional Steering of Large Language Models with Steering Tokens
by: Radevski, Gorjan, et al.
Published: (2026)

Steering to Say No: Configurable Refusal via Activation Steering in Vision Language Models
by: Yang, Jiaxi, et al.
Published: (2026)

From Foresight to Forethought: VLM-In-the-Loop Policy Steering via Latent Alignment
by: Wu, Yilin, et al.
Published: (2025)

Manifold-Guided Attention Steering
by: Li, Ian, et al.
Published: (2026)

DSPA: Dynamic SAE Steering for Data-Efficient Preference Alignment
by: Wedgwood, James, et al.
Published: (2026)

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

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

Conceptors for Semantic Steering
by: Triantafyllopoulos, Ilias, et al.
Published: (2026)