Inference-Time Machine Unlearning via Gated Activation Redirection

arXiv:2605.12765 · cs.LG · Submitted 2026-05-12 · Read on arXiv

cs.LG

Submitted: 2026-05-12

Updated: 2026-10-08

Code: https://github.com/ViniTurani/GUARD-IT

Terminology

• Steering — 3× in this paper · explained in 2 episodes
• Activation Steering — 2× in this paper · explained in 4 episodes
• Machine Unlearning — 2× in this paper · explained in 3 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Quantization — 1× in this paper · explained in 12 episodes

Sources

• Quantization-Robust LLM Unlearning via Low-Rank Adaptation
• Toy Models of Superposition
• Applying sparse autoencoders to unlearn knowledge in language models
• The Llama 3 Herd of Models
• Model Internal Sleuthing: Finding Lexical Identity and Inflectional Features in Modern Language Models
• The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
• Large Language Model Unlearning via Embedding-Corrupted Prompts
• TOFU: A Task of Fictitious Unlearning for LLMs
• The Geometry of Categorical and Hierarchical Concepts in Large Language Models
• Ignore Previous Prompt: Attack Techniques For Language Models
• LLM Unlearning via Neural Activation Redirection
• Layer by Layer: Uncovering Hidden Representations in Language Models
• Gemma 4 Technical Report
• Guardrail Baselines for Unlearning in LLMs
• BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of Information Retrieval Models
• Steering Language Models With Activation Engineering
• CE-U: Cross Entropy Unlearning
• Spherical Steering: Geometry-Aware Activation Rotation for Language Models
• Catastrophic Failure of LLM Unlearning via Quantization
• Representation Engineering: A Top-Down Approach to AI Transparency

Related papers

• Polynomial-Augmented Neural Networks (PANNs) with Weak Orthogonality Constraints for Enhanced Function and PDE Approximation
• AIRL-S: Unifying Reinforcement Learning and Search-Based Test-Time Scaling via Adversarial Inverse Reinforcement Learning
• Transformers as Bayesian In-Context Experimenters: Smoothness-Adaptive Efficient ATE Estimation
• Convergence issues in Relational Concept Analysis based on AOC-posets
• Beliefs Beyond Posteriors: The Predictive Cost of ELBO Binding
• Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks