Image de couverture de livre

Steering Awareness: Detecting Activation Steering from Within

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Rivera, Joshua Fonseca, Africa, David Demitri
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

LURE: Live-Usage Replay Evaluations for Reducing Evaluation Awareness
par: Ivanov, Igor, et autres
Publié: (2026)

HyperSteer: Activation Steering at Scale with Hypernetworks
par: Sun, Jiuding, et autres
Publié: (2025)

Steer Like the LLM: Activation Steering that Mimics Prompting
par: Heyman, Geert, et autres
Publié: (2026)

Consistency Training while Mitigating Obfuscation via Rate Matching
par: Imran, Sohaib, et autres
Publié: (2026)

Fusion Steering: Prompt-Specific Activation Control
par: Chang, Waldemar, et autres
Publié: (2025)

Activation Scaling for Steering and Interpreting Language Models
par: Stoehr, Niklas, et autres
Publié: (2024)

Learning Dynamics of Meta-Learning in Small Model Pretraining
par: Africa, David Demitri, et autres
Publié: (2025)

Investigating ReLoRA: Effects on the Learning Dynamics of Small Language Models
par: Weiss, Yuval, et autres
Publié: (2025)

Self-Steering Language Models
par: Grand, Gabriel, et autres
Publié: (2025)

Cross-Lingual Activation Steering for Multilingual Language Models
par: Pokharel, Rhitabrat, et autres
Publié: (2026)

SAKE: Steering Activations for Knowledge Editing
par: Scialanga, Marco, et autres
Publié: (2025)

Programming Refusal with Conditional Activation Steering
par: Lee, Bruce W., et autres
Publié: (2024)

Probing and Steering Evaluation Awareness of Language Models
par: Nguyen, Jord, et autres
Publié: (2025)

Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions
par: Kang, Diancheng, et autres
Publié: (2026)

Hallucination reduction with CASAL: Contrastive Activation Steering For Amortized Learning
par: Wannan, et autres
Publié: (2025)

Meta-Pretraining for Zero-Shot Cross-Lingual Named Entity Recognition in Low-Resource Philippine Languages
par: Africa, David Demitri, et autres
Publié: (2025)

Extracting Unlearned Information from LLMs with Activation Steering
par: Seyitoğlu, Atakan, et autres
Publié: (2024)

Endogenous Resistance to Activation Steering in Language Models
par: McKenzie, Alex, et autres
Publié: (2026)

Investigating Bias Representations in Llama 2 Chat via Activation Steering
par: Lu, Dawn, et autres
Publié: (2024)

Steering When Necessary: Flexible Steering Large Language Models with Backtracking
par: Cheng, Zifeng, et autres
Publié: (2025)

Steering Evaluation-Aware Language Models to Act Like They Are Deployed
par: Hua, Tim Tian, et autres
Publié: (2025)

Steering Llama 2 via Contrastive Activation Addition
par: Panickssery, Nina, et autres
Publié: (2023)

EasySteer: A Unified Framework for High-Performance and Extensible LLM Steering
par: Xu, Haolei, et autres
Publié: (2025)

CoSteer: Collaborative Decoding-Time Personalization via Local Delta Steering
par: Lv, Hang, et autres
Publié: (2025)

LinEAS: End-to-end Learning of Activation Steering with a Distributional Loss
par: Rodriguez, Pau, et autres
Publié: (2025)

ASRU: Activation Steering Meets Reinforcement Unlearning for Multimodal Large Language Models
par: Guang, Jiahui, et autres
Publié: (2026)

No Answer Needed: Predicting LLM Answer Accuracy from Question-Only Linear Probes
par: Cencerrado, Iván Vicente Moreno, et autres
Publié: (2025)

Inoculation Prompting: Eliciting traits from LLMs during training can suppress them at test-time
par: Tan, Daniel, et autres
Publié: (2025)

Steer LLM Latents for Hallucination Detection
par: Park, Seongheon, et autres
Publié: (2025)

Pico: A Modular Framework for Hypothesis-Driven Small Language Model Research
par: Martinez, Richard Diehl, et autres
Publié: (2025)

Extending Activation Steering to Broad Skills and Multiple Behaviours
par: van der Weij, Teun, et autres
Publié: (2024)

EmoShift: Lightweight Activation Steering for Enhanced Emotion-Aware Speech Synthesis
par: Zhou, Li, et autres
Publié: (2026)

SAGE: Steering Dialog Generation with Future-Aware State-Action Augmentation
par: Zhang, Yizhe, et autres
Publié: (2025)

Steering Multimodal Large Language Models Decoding for Context-Aware Safety
par: Liu, Zheyuan, et autres
Publié: (2025)

Compositional Steering of Large Language Models with Steering Tokens
par: Radevski, Gorjan, et autres
Publié: (2026)

Improving Instruction-Following in Language Models through Activation Steering
par: Stolfo, Alessandro, et autres
Publié: (2024)

Mitigating Content Effects on Reasoning in Language Models through Fine-Grained Activation Steering
par: Valentino, Marco, et autres
Publié: (2025)

SteeringSafety: A Systematic Safety Evaluation Framework of Representation Steering in LLMs
par: Siu, Vincent, et autres
Publié: (2025)

CogSteer: Cognition-Inspired Selective Layer Intervention for Efficiently Steering Large Language Models
par: Wang, Xintong, et autres
Publié: (2024)

Detecting and Steering LLMs' Empathy in Action
par: Cadile, Juan P.
Publié: (2025)