Stress Testing Unlearning Algorithms
cs.LG
Submitted: 2026-08-23
Updated: 2026-09-01
Comments: Added appendices, corrected the order of the authors in the article
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- CRISP: Persistent Concept Unlearning via Sparse Autoencoders
- Who's Harry Potter? Approximate Unlearning in LLMs
- The Llama 3 Herd of Models
- BLUR: A Benchmark for LLM Unlearning Robust to Forget-Retain Overlap
- The WMDP Benchmark: Measuring and Reducing Malicious Use With Unlearning
- An Adversarial Perspective on Machine Unlearning for AI Safety
- TOFU: A Task of Fictitious Unlearning for LLMs
- SoK: Machine Unlearning for Large Language Models
- Great, Now Write an Article About That: The Crescendo Multi-Turn LLM Jailbreak Attack
- Go Beyond Your Means: Unlearning with Per-Sample Gradient Orthogonalization
- "Do Anything Now": Characterizing and Evaluating In-The-Wild Jailbreak Prompts on Large Language Models
- MUSE: Machine Unlearning Six-Way Evaluation for Language Models
- UnUnlearning: Unlearning is not sufficient for content regulation in advanced generative AI
- Zephyr: Direct Distillation of LM Alignment
- Jailbreak Attacks and Defenses Against Large Language Models: A Survey
- Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning
- Universal and Transferable Adversarial Attacks on Aligned Language Models
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: Local-Consistency Optimisation for Bayesian Neural Networks
- Understanding Diffusion Models via Ratio-Based Function Approximation with SignReLU Networks