Saved in:
| Main Author: | Petrov, Valentin |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2603.22061 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Similar Items
An Embarrassingly Simple Defense Against LLM Abliteration Attacks
by: Shairah, Harethah Abu, et al.
Published: (2025)
by: Shairah, Harethah Abu, et al.
Published: (2025)
SOM Directions are Better than One: Multi-Directional Refusal Suppression in Language Models
by: Piras, Giorgio, et al.
Published: (2025)
by: Piras, Giorgio, et al.
Published: (2025)
Feature-Guided SAE Steering for Refusal-Rate Control using Contrasting Prompts
by: Bhargav, Samaksh, et al.
Published: (2025)
by: Bhargav, Samaksh, et al.
Published: (2025)
Refusal in Language Models Is Mediated by a Single Direction
by: Arditi, Andy, et al.
Published: (2024)
by: Arditi, Andy, et al.
Published: (2024)
Agentopic: A Generative AI Agent Workflow for Explainable Topic Modeling
by: Kok-Shun, Brice Valentin, et al.
Published: (2026)
by: Kok-Shun, Brice Valentin, et al.
Published: (2026)
RefusalBench: Generative Evaluation of Selective Refusal in Grounded Language Models
by: Muhamed, Aashiq, et al.
Published: (2025)
by: Muhamed, Aashiq, et al.
Published: (2025)
Efficient Refusal Ablation in LLM through Optimal Transport
by: Nanfack, Geraldin, et al.
Published: (2026)
by: Nanfack, Geraldin, et al.
Published: (2026)
Geometric Erasure by Contrastive Velocity Matching in Rectified Flows
by: Grebe, Jonas Henry, et al.
Published: (2026)
by: Grebe, Jonas Henry, et al.
Published: (2026)
Counting Clues: A Lightweight Probabilistic Baseline Can Match an LLM
by: Jia, Furong, et al.
Published: (2025)
by: Jia, Furong, et al.
Published: (2025)
Step-Wise Refusal Dynamics in Autoregressive and Diffusion Language Models
by: Rahimi, Eliron, et al.
Published: (2026)
by: Rahimi, Eliron, et al.
Published: (2026)
Where Do Reasoning Models Refuse?
by: Yamaguchi, Kureha, et al.
Published: (2025)
by: Yamaguchi, Kureha, et al.
Published: (2025)
Programming Refusal with Conditional Activation Steering
by: Lee, Bruce W., et al.
Published: (2024)
by: Lee, Bruce W., et al.
Published: (2024)
Tracing the Dynamics of Refusal: Exploiting Latent Refusal Trajectories for Robust Jailbreak Detection
by: Hu, Xulin, et al.
Published: (2026)
by: Hu, Xulin, et al.
Published: (2026)
CoSD: Collaborative Stance Detection with Contrastive Heterogeneous Topic Graph Learning
by: Cheng, Yinghan, et al.
Published: (2024)
by: Cheng, Yinghan, et al.
Published: (2024)
Flow Matching in the Low-Noise Regime: Pathologies and a Contrastive Remedy
by: Zeng, Weili, et al.
Published: (2025)
by: Zeng, Weili, et al.
Published: (2025)
Distinguishable Deletion: Unifying Knowledge Erasure and Refusal for Large Language Model Unlearning
by: Yang, Puning, et al.
Published: (2026)
by: Yang, Puning, et al.
Published: (2026)
Integrating Distribution Matching into Semi-Supervised Contrastive Learning for Labeled and Unlabeled Data
by: Nakayama, Shogo, et al.
Published: (2026)
by: Nakayama, Shogo, et al.
Published: (2026)
Topic Modeling and Link-Prediction for Material Property Discovery
by: Barron, Ryan C., et al.
Published: (2025)
by: Barron, Ryan C., et al.
Published: (2025)
Furina: Fragmented Uncertainty-Driven Refusal Instability Attack
by: Wu, Tongxi, et al.
Published: (2026)
by: Wu, Tongxi, et al.
Published: (2026)
Model Failure or Data Corruption? Exploring Inconsistencies in Building Energy Ratings with Self-Supervised Contrastive Learning
by: Xiao, Qian, et al.
Published: (2024)
by: Xiao, Qian, et al.
Published: (2024)
Does Refusal Training in LLMs Generalize to the Past Tense?
by: Andriushchenko, Maksym, et al.
Published: (2024)
by: Andriushchenko, Maksym, et al.
Published: (2024)
The Struggle Between Continuation and Refusal: A Mechanistic Analysis of the Continuation-Triggered Jailbreak in LLMs
by: Deng, Yonghong, et al.
Published: (2026)
by: Deng, Yonghong, et al.
Published: (2026)
Merging Embedded Topics with Optimal Transport for Online Topic Modeling on Data Streams
by: Granese, Federica, et al.
Published: (2025)
by: Granese, Federica, et al.
Published: (2025)
An Iterative Approach to Topic Modelling
by: Wong, Albert, et al.
Published: (2024)
by: Wong, Albert, et al.
Published: (2024)
Refusing Safe Prompts for Multi-modal Large Language Models
by: Shao, Zedian, et al.
Published: (2024)
by: Shao, Zedian, et al.
Published: (2024)
Just Enough Shifts: Mitigating Over-Refusal in Aligned Language Models with Targeted Representation Fine-Tuning
by: Dabas, Mahavir, et al.
Published: (2025)
by: Dabas, Mahavir, et al.
Published: (2025)
Simple Baselines are Competitive with Code Evolution
by: Gideoni, Yonatan, et al.
Published: (2026)
by: Gideoni, Yonatan, et al.
Published: (2026)
Integrated Influence: Data Attribution with Baseline
by: Yang, Linxiao, et al.
Published: (2025)
by: Yang, Linxiao, et al.
Published: (2025)
minimax: Efficient Baselines for Autocurricula in JAX
by: Jiang, Minqi, et al.
Published: (2023)
by: Jiang, Minqi, et al.
Published: (2023)
Learning Multi-Agent Communication with Contrastive Learning
by: Lo, Yat Long, et al.
Published: (2023)
by: Lo, Yat Long, et al.
Published: (2023)
The Geometry of Refusal in Large Language Models: Concept Cones and Representational Independence
by: Wollschläger, Tom, et al.
Published: (2025)
by: Wollschläger, Tom, et al.
Published: (2025)
AlphaSteer: Learning Refusal Steering with Principled Null-Space Constraint
by: Sheng, Leheng, et al.
Published: (2025)
by: Sheng, Leheng, et al.
Published: (2025)
TopicProphet: Prophesies on Temporal Topic Trends and Stocks
by: Kim, Olivia
Published: (2025)
by: Kim, Olivia
Published: (2025)
DirectMultiStep: Direct Route Generation for Multistep Retrosynthesis
by: Shee, Yu, et al.
Published: (2024)
by: Shee, Yu, et al.
Published: (2024)
Learnable Chernoff Baselines for Inference-Time Alignment
by: Madhow, Sunil, et al.
Published: (2026)
by: Madhow, Sunil, et al.
Published: (2026)
Tensor-Fused Multi-View Graph Contrastive Learning
by: Wu, Yujia, et al.
Published: (2024)
by: Wu, Yujia, et al.
Published: (2024)
Detection Is Cheap, Routing Is Learned: Why Refusal-Based Alignment Evaluation Fails
by: Frank, Gregory N.
Published: (2026)
by: Frank, Gregory N.
Published: (2026)
What Drives Representation Steering? A Mechanistic Case Study on Steering Refusal
by: Cheng, Stephen, et al.
Published: (2026)
by: Cheng, Stephen, et al.
Published: (2026)
When Refusals Fail: Unstable Safety Mechanisms in Long-Context LLM Agents
by: Hadeliya, Tsimur, et al.
Published: (2025)
by: Hadeliya, Tsimur, et al.
Published: (2025)
Failure Modes in Multi-Hop QA: The Weakest Link Effect and the Recognition Bottleneck
by: Zhang, Meiru, et al.
Published: (2026)
by: Zhang, Meiru, et al.
Published: (2026)
Similar Items
-
An Embarrassingly Simple Defense Against LLM Abliteration Attacks
by: Shairah, Harethah Abu, et al.
Published: (2025) -
SOM Directions are Better than One: Multi-Directional Refusal Suppression in Language Models
by: Piras, Giorgio, et al.
Published: (2025) -
Feature-Guided SAE Steering for Refusal-Rate Control using Contrasting Prompts
by: Bhargav, Samaksh, et al.
Published: (2025) -
Refusal in Language Models Is Mediated by a Single Direction
by: Arditi, Andy, et al.
Published: (2024) -
Agentopic: A Generative AI Agent Workflow for Explainable Topic Modeling
by: Kok-Shun, Brice Valentin, et al.
Published: (2026)