Cover Image

Refusal in Language Models Is Mediated by a Single Direction

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Arditi, Andy, Obeso, Oscar, Syed, Aaquib, Paleka, Daniel, Panickssery, Nina, Gurnee, Wes, Nanda, Neel
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

Real-Time Detection of Hallucinated Entities in Long-Form Generation
by: Obeso, Oscar, et al.
Published: (2025)

Language Models Represent Space and Time
by: Gurnee, Wes, et al.
Published: (2023)

Confidence Regulation Neurons in Language Models
by: Stolfo, Alessandro, et al.
Published: (2024)

Do I Know This Entity? Knowledge Awareness and Hallucinations in Language Models
by: Ferrando, Javier, et al.
Published: (2024)

Where Do Reasoning Models Refuse?
by: Yamaguchi, Kureha, et al.
Published: (2025)

Universal Neurons in GPT2 Language Models
by: Gurnee, Wes, et al.
Published: (2024)

Understanding Jailbreak Success: A Study of Latent Space Dynamics in Large Language Models
by: Ball, Sarah, et al.
Published: (2024)

Explorations of Self-Repair in Language Models
by: Rushing, Cody, et al.
Published: (2024)

Inspection and Control of Self-Generated-Text Recognition Ability in Llama3-8b-Instruct
by: Ackerman, Christopher, et al.
Published: (2024)

The Remarkable Robustness of LLMs: Stages of Inference?
by: Lad, Vedang, et al.
Published: (2024)

Towards Best Practices of Activation Patching in Language Models: Metrics and Methods
by: Zhang, Fred, et al.
Published: (2023)

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

Consistency Checks for Language Model Forecasters
by: Paleka, Daniel, et al.
Published: (2024)

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

Thought Branches: Interpreting LLM Reasoning Requires Resampling
by: Macar, Uzay, et al.
Published: (2025)

Thought Anchors: Which LLM Reasoning Steps Matter?
by: Bogdan, Paul C., et al.
Published: (2025)

The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence
by: Wollschläger, Tom, et al.
Published: (2025)

What's the plan? Metrics for implicit planning in LLMs and their application to rhyme generation and question answering
by: Maar, Jim, et al.
Published: (2026)

Scaling sparse feature circuit finding for in-context learning
by: Kharlapenko, Dmitrii, et al.
Published: (2025)

Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning
by: Minder, Julian, et al.
Published: (2025)

Mitigating Many-Shot Jailbreaking
by: Ackerman, Christopher M., et al.
Published: (2025)

Probing Persona-Dependent Preferences in Language Models
by: Gilg, Oscar, et al.
Published: (2026)

Pitfalls in Evaluating Language Model Forecasters
by: Paleka, Daniel, et al.
Published: (2025)

Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning
by: Casademunt, Helena, et al.
Published: (2025)

Chain-of-Thought Reasoning In The Wild Is Not Always Faithful
by: Arcuschin, Iván, et al.
Published: (2025)

Censored LLMs as a Natural Testbed for Secret Knowledge Elicitation
by: Casademunt, Helena, et al.
Published: (2026)

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

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

Building Production-Ready Probes For Gemini
by: Kramár, János, et al.
Published: (2026)

Data Cartography for Detecting Memorization Hotspots and Guiding Data Interventions in Generative Models
by: Patel, Laksh, et al.
Published: (2025)

SOM Directions are Better than One: Multi-Directional Refusal Suppression in Language Models
by: Piras, Giorgio, et al.
Published: (2025)

Understanding Reasoning in Thinking Language Models via Steering Vectors
by: Venhoff, Constantin, et al.
Published: (2025)

Does Refusal Training in LLMs Generalize to the Past Tense?
by: Andriushchenko, Maksym, et al.
Published: (2024)

Tracing the Dynamics of Refusal: Exploiting Latent Refusal Trajectories for Robust Jailbreak Detection
by: Hu, Xulin, et al.
Published: (2026)

Weird Generalization and Inductive Backdoors: New Ways to Corrupt LLMs
by: Betley, Jan, et al.
Published: (2025)

BatchTopK Sparse Autoencoders
by: Bussmann, Bart, et al.
Published: (2024)

Gradient Cuff: Detecting Jailbreak Attacks on Large Language Models by Exploring Refusal Loss Landscapes
by: Hu, Xiaomeng, et al.
Published: (2024)

Detection Is Cheap, Routing Is Learned: Why Refusal-Based Alignment Evaluation Fails
by: Frank, Gregory N.
Published: (2026)

When Refusals Fail: Unstable Safety Mechanisms in Long-Context LLM Agents
by: Hadeliya, Tsimur, et al.
Published: (2025)

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