Adaptive Localization of Knowledge Negation for Continual LLM Unlearning
cs.LG
Submitted: 2026-11-02
Updated: 2026-11-02
Code: https://github.com/zaocan666/ALKN
Terminology
Sources
- Digital Forgetting in Large Language Models: A Survey of Unlearning Methods
- Who's Harry Potter? Approximate Unlearning in LLMs
- Certified Data Removal from Machine Learning Models
- Intrinsic Test of Unlearning Using Parametric Knowledge Traces
- Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference
- WAGLE: Strategic Weight Attribution for Effective and Modular Unlearning in Large Language Models
- Rethinking Machine Unlearning for Large Language Models
- Eight Methods to Evaluate Robust Unlearning in LLMs
- TOFU: A Task of Fictitious Unlearning for LLMs
- Code Llama: Open Foundation Models for Code
- A Probabilistic Perspective on Unlearning and Alignment for Large Language Models
- MUSE: Machine Unlearning Six-Way Evaluation for Language Models
- Position: LLM Unlearning Benchmarks are Weak Measures of Progress
- Towards Effective Evaluations and Comparisons for LLM Unlearning Methods
- Evaluating Deep Unlearning in Large Language Models
- Large Language Model Unlearning
- A Closer Look at Machine Unlearning for Large Language Models
- Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning
- In-context Demonstration Matters: On Prompt Optimization for Pseudo-Supervision Refinement
- A Survey of Large Language Models
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