Extracting Forgotten Prompts from Targeted Unlearned Models
cs.LG
Submitted: 2026-09-03
Updated: 2026-09-03
Terminology
Sources
- TOFU: A Task of Fictitious Unlearning for LLMs
- How Data Inter-connectivity Shapes LLMs Unlearning: A Structural Unlearning Perspective
- DUSK: Do Not Unlearn Shared Knowledge
- MUSE: Machine Unlearning Six-Way Evaluation for Language Models
- Step-by-Step Reasoning Attack: Revealing 'Erased' Knowledge in Large Language Models
- Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning
- Effective Prompt Extraction from 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