Unlearning by Extrapolating a Shrink-and-Heal Lookahead
cs.LG, cs.CL
Submitted: 2026-10-30
Updated: 2026-10-30
Terminology
Sources
- Distance Is Not Enough: Forget-Retain Alignment Gap Predicts LLM Relearning Robustness
- Do Unlearning Methods Remove Information from Language Model Weights?
- Fast Unlearning at Scale via Margin Self-Correction
- Who's Harry Potter? Approximate Unlearning in LLMs
- Eight Methods to Evaluate Robust Unlearning in LLMs
- Forget Narrowly, Retain Broadly: Unlearning as an Asymmetric Generalization Problem
- Forgetting That Sticks: Quantization-Permanent Unlearning via Circuit Attribution
- A Theoretical Framework for LLM Fine-tuning Using Early Stopping for Non-random Initialization
- Unlearning What Matters: Token-Level Attribution for Precise Language Model Unlearning
- Robust LLM Unlearning Against Relearning Attacks: The Minor Components in Representations Matter
- CE-U: Cross Entropy Unlearning
- Crossing the Margin Cliff: Toward Relearn-Robust LLM Unlearning via Margin Calibration
- SAGE: Retain-Aware Post-Hoc Sanitization of Final Unlearning Vector
Related papers
- A Physics-Regulated Neural Framework for Learning 3D Grain Growth Dynamics
- FlexMoE: Learning One-for-All Multi-Budget Expert Pruning for Flexible MoE Deployment
- OptiMind: Improving Small Language Models for Optimization Modeling through Formulation Guidance and Multi-Turn Learning
- Staying in the Sweet Spot: Boost Reasoning Evolution via Responsive Rollout Difficulty Manipulation
- Examining the Impact of Data and Training Methods on Emergent and Subliminal Misalignment
- Rethinking Black-Box On-Policy Distillation: A Rubric-based Analysis