Cover Image

Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Kang, Diancheng, Liu, Zheyuan, Ma, Ningshan, Huang, Yue, Tan, Zhaoxuan, Jiang, Meng
Format:	Preprint
Published:	2026
Subjects:	Computation and Language Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

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

Fusion Steering: Prompt-Specific Activation Control
by: Chang, Waldemar, et al.
Published: (2025)

Machine Unlearning in Generative AI: A Survey
by: Liu, Zheyuan, et al.
Published: (2024)

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

Protecting Privacy in Multimodal Large Language Models with MLLMU-Bench
by: Liu, Zheyuan, et al.
Published: (2024)

MTMCS-Bench: Evaluating Contextual Safety of Multimodal Large Language Models in Multi-Turn Dialogues
by: Liu, Zheyuan, et al.
Published: (2026)

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

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

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

Improving Instruction-Following in Language Models through Activation Steering
by: Stolfo, Alessandro, et al.
Published: (2024)

Activation Scaling for Steering and Interpreting Language Models
by: Stoehr, Niklas, et al.
Published: (2024)

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

DESTEIN: Navigating Detoxification of Language Models via Universal Steering Pairs and Head-wise Activation Fusion
by: Li, Yu, et al.
Published: (2024)

Steering Llama 2 via Contrastive Activation Addition
by: Panickssery, Nina, et al.
Published: (2023)

Towards Adaptive Mechanism Activation in Language Agent
by: Huang, Ziyang, et al.
Published: (2024)

Cross-Lingual Activation Steering for Multilingual Language Models
by: Pokharel, Rhitabrat, et al.
Published: (2026)

Personalized Pieces: Efficient Personalized Large Language Models through Collaborative Efforts
by: Tan, Zhaoxuan, et al.
Published: (2024)

Programming Refusal with Conditional Activation Steering
by: Lee, Bruce W., et al.
Published: (2024)

SAKE: Steering Activations for Knowledge Editing
by: Scialanga, Marco, et al.
Published: (2025)

Hallucination reduction with CASAL: Contrastive Activation Steering For Amortized Learning
by: Wannan, et al.
Published: (2025)

Interpretable Steering of Large Language Models with Feature Guided Activation Additions
by: Soo, Samuel, et al.
Published: (2025)

Steering Language Models Before They Speak: Logit-Level Interventions
by: An, Hyeseon, et al.
Published: (2026)

Dual-Space Smoothness for Robust and Balanced LLM Unlearning
by: Yan, Han, et al.
Published: (2025)

Endogenous Resistance to Activation Steering in Language Models
by: McKenzie, Alex, et al.
Published: (2026)

ASRU: Activation Steering Meets Reinforcement Unlearning for Multimodal Large Language Models
by: Guang, Jiahui, et al.
Published: (2026)

LinEAS: End-to-end Learning of Activation Steering with a Distributional Loss
by: Rodriguez, Pau, et al.
Published: (2025)

Extracting Unlearned Information from LLMs with Activation Steering
by: Seyitoğlu, Atakan, et al.
Published: (2024)

Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categories
by: Wang, Tianlong, et al.
Published: (2024)

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

Mitigating Content Effects on Reasoning in Language Models through Fine-Grained Activation Steering
by: Valentino, Marco, et al.
Published: (2025)

Extending Activation Steering to Broad Skills and Multiple Behaviours
by: van der Weij, Teun, et al.
Published: (2024)

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

The Spike, the Sparse and the Sink: Anatomy of Massive Activations and Attention Sinks
by: Sun, Shangwen, et al.
Published: (2026)

Multi-property Steering of Large Language Models with Dynamic Activation Composition
by: Scalena, Daniel, et al.
Published: (2024)

Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steering
by: Bigelow, Eric, et al.
Published: (2025)

ContextFocus: Activation Steering for Contextual Faithfulness in Large Language Models
by: Anand, Nikhil, et al.
Published: (2026)

EmoShift: Lightweight Activation Steering for Enhanced Emotion-Aware Speech Synthesis
by: Zhou, Li, et al.
Published: (2026)

Beyond Prompt: Fine-grained Simulation of Cognitively Impaired Standardized Patients via Stochastic Steering
by: Zhang, Weikang, et al.
Published: (2026)

SR-KI: Scalable and Real-Time Knowledge Integration into LLMs via Supervised Attention
by: Yu, Bohan, et al.
Published: (2025)

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