Cover Image

Guiding Giants: Lightweight Controllers for Weighted Activation Steering in LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hegazy, Amr, Elhoushi, Mostafa, Alanwar, Amr
Format:	Preprint
Published:	2025
Subjects:	Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Safe LLM-Controlled Robots with Formal Guarantees via Reachability Analysis
by: Hafez, Ahmad, et al.
Published: (2025)

Data-Driven Safety Verification using Barrier Certificates and Matrix Zonotopes
by: Oumer, Mohammed Adib, et al.
Published: (2025)

Evaluation of LLMs on Syntax-Aware Code Fill-in-the-Middle Tasks
by: Gong, Linyuan, et al.
Published: (2024)

AST-T5: Structure-Aware Pretraining for Code Generation and Understanding
by: Gong, Linyuan, et al.
Published: (2024)

Steering MoE LLMs via Expert (De)Activation
by: Fayyaz, Mohsen, et al.
Published: (2025)

Understanding How CodeLLMs (Mis)Predict Types with Activation Steering
by: Lucchetti, Francesca, et al.
Published: (2024)

Online Data-Driven Reachability Analysis using Zonotopic Recursive Least Squares
by: Akhormeh, Alireza Naderi, et al.
Published: (2025)

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

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

Steering Language Models with Weight Arithmetic
by: Fierro, Constanza, et al.
Published: (2025)

Diversity of Thought Elicits Stronger Reasoning Capabilities in Multi-Agent Debate Frameworks
by: Hegazy, Mahmood
Published: (2024)

Steering Language Models With Activation Engineering
by: Turner, Alexander Matt, et al.
Published: (2023)

any4: Learned 4-bit Numeric Representation for LLMs
by: Elhoushi, Mostafa, et al.
Published: (2025)

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

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

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

Sentiment Classification of Gaza War Headlines: A Comparative Analysis of Large Language Models and Arabic Fine-Tuned BERT Models
by: Eleraqi, Amr, et al.
Published: (2026)

CHAI: Clustered Head Attention for Efficient LLM Inference
by: Agarwal, Saurabh, et al.
Published: (2024)

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

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

From Words to Collisions: LLM-Guided Evaluation and Adversarial Generation of Safety-Critical Driving Scenarios
by: Gao, Yuan, et al.
Published: (2025)

Curriculum Learning and Pseudo-Labeling Improve the Generalization of Multi-Label Arabic Dialect Identification Models
by: Mekky, Ali, et al.
Published: (2026)

Spherical Steering: Geometry-Aware Activation Rotation for Language Models
by: You, Zejia, et al.
Published: (2026)

Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation
by: Abdelnabi, Sahar, et al.
Published: (2023)

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

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

FishBack: Pullback Fisher Geometry for Optimal Activation Steering in Transformers
by: Wang, Sihan, et al.
Published: (2026)

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

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

Steering LLMs for Formal Theorem Proving
by: Kirtania, Shashank, et al.
Published: (2025)

SteeringSafety: A Systematic Safety Evaluation Framework of Representation Steering in LLMs
by: Siu, Vincent, et al.
Published: (2025)

Privacy-Preserving Transformers: SwiftKey's Differential Privacy Implementation
by: Abouelenin, Abdelrahman, et al.
Published: (2025)

Markovian Generation Chains in Large Language Models
by: Geng, Mingmeng, et al.
Published: (2026)

Structuring Radiology Reports: Challenging LLMs with Lightweight Models
by: Moll, Johannes, et al.
Published: (2025)

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

Activation Steering via Generative Causal Mediation
by: Sankaranarayanan, Aruna, et al.
Published: (2026)

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

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

Agile-Quant: Activation-Guided Quantization for Faster Inference of LLMs on the Edge
by: Shen, Xuan, et al.
Published: (2023)

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