Cover Image

Programming Refusal with Conditional Activation Steering

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Lee, Bruce W., Padhi, Inkit, Ramamurthy, Karthikeyan Natesan, Miehling, Erik, Dognin, Pierre, Nagireddy, Manish, Dhurandhar, Amit
Format:	Preprint
Published:	2024
Subjects:	Machine Learning Artificial Intelligence Computation and Language
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Value Alignment from Unstructured Text
by: Padhi, Inkit, et al.
Published: (2024)

Ranking Large Language Models without Ground Truth
by: Dhurandhar, Amit, et al.
Published: (2024)

CELL your Model: Contrastive Explanations for Large Language Models
by: Luss, Ronny, et al.
Published: (2024)

Trust Regions for Explanations via Black-Box Probabilistic Certification
by: Dhurandhar, Amit, et al.
Published: (2024)

Evaluating the Prompt Steerability of Large Language Models
by: Miehling, Erik, et al.
Published: (2024)

Final-Model-Only Data Attribution with a Unifying View of Gradient-Based Methods
by: Wei, Dennis, et al.
Published: (2024)

Alignment Studio: Aligning Large Language Models to Particular Contextual Regulations
by: Achintalwar, Swapnaja, et al.
Published: (2024)

AI Steerability 360: A Toolkit for Steering Large Language Models
by: Miehling, Erik, et al.
Published: (2026)

Contextual Moral Value Alignment Through Context-Based Aggregation
by: Dognin, Pierre, et al.
Published: (2024)

Multi-Level Explanations for Generative Language Models
by: Paes, Lucas Monteiro, et al.
Published: (2024)

Sparsity May Be All You Need: Sparse Random Parameter Adaptation
by: Rios, Jesus, et al.
Published: (2025)

Answering the Wrong Question: Reasoning Trace Inversion for Abstention in LLMs
by: Gourabathina, Abinitha, et al.
Published: (2026)

Protecting Users From Themselves: Safeguarding Contextual Privacy in Interactions with Conversational Agents
by: Ngong, Ivoline, et al.
Published: (2025)

When in Doubt, Cascade: Towards Building Efficient and Capable Guardrails
by: Nagireddy, Manish, et al.
Published: (2024)

Reasoning about concepts with LLMs: Inconsistencies abound
by: Uceda-Sosa, Rosario, et al.
Published: (2024)

Split, Unlearn, Merge: Leveraging Data Attributes for More Effective Unlearning in LLMs
by: Kadhe, Swanand Ravindra, et al.
Published: (2024)

Identifying Sub-networks in Neural Networks via Functionally Similar Representations
by: Gao, Tian, et al.
Published: (2024)

Language Models in Dialogue: Conversational Maxims for Human-AI Interactions
by: Miehling, Erik, et al.
Published: (2024)

Building a Foundational Guardrail for General Agentic Systems via Synthetic Data
by: Huang, Yue, et al.
Published: (2025)

Language Models Coupled with Metacognition Can Outperform Reasoning Models
by: Khandelwal, Vedant, et al.
Published: (2025)

Cross-Examiner: Evaluating Consistency of Large Language Model-Generated Explanations
by: Villa, Danielle, et al.
Published: (2025)

What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal
by: Cheng, Stephen, et al.
Published: (2026)

AgentSCOPE: Evaluating Contextual Privacy Across Agentic Workflows
by: Ngong, Ivoline C., et al.
Published: (2026)

Mitigating Misalignment Contagion by Steering with Implicit Traits
by: Chang, Maria, et al.
Published: (2026)

WikiContradict: A Benchmark for Evaluating LLMs on Real-World Knowledge Conflicts from Wikipedia
by: Hou, Yufang, et al.
Published: (2024)

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

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

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

Large Language Model Confidence Estimation via Black-Box Access
by: Pedapati, Tejaswini, et al.
Published: (2024)

Agentic AI Needs a Systems Theory
by: Miehling, Erik, et al.
Published: (2025)

ICX360: In-Context eXplainability 360 Toolkit
by: Wei, Dennis, et al.
Published: (2025)

RepIt: Steering Language Models with Concept-Specific Refusal Vectors
by: Siu, Vincent, et al.
Published: (2025)

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

Refusal Steering: Fine-grained Control over LLM Refusal Behaviour for Sensitive Topics
by: García-Ferrero, Iker, et al.
Published: (2025)

LCGuard: Latent Communication Guard for Safe KV Sharing in Multi-Agent Systems
by: Asif, Sadia, et al.
Published: (2026)

When Stability meets Sufficiency: Informative Explanations that do not Overwhelm
by: Luss, Ronny, et al.
Published: (2021)

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

RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models
by: Muhamed, Aashiq, et al.
Published: (2025)

Mitigating Over-Refusal in Aligned Large Language Models via Inference-Time Activation Energy
by: Jiang, Eric Hanchen, et al.
Published: (2025)

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