GONE: Structural Knowledge Unlearning via Neighborhood-Expanded Distribution Shaping
cs.CL, cs.LG
Submitted: 2026-02-21
Updated: 2026-09-01
Code: https://github.com/deepseek-ai/DeepSeek-V3
Terminology
Sources
- Machine Unlearning
- Mass-Editing Memory in a Transformer
- How Data Inter-connectivity Shapes LLMs Unlearning: A Structural Unlearning Perspective
- Who's Harry Potter? Approximate Unlearning in LLMs
- Direct Preference Optimization: Your Language Model is Secretly a Reward Model
- AlphaEdit: Null-Space Constrained Knowledge Editing for Language Models
- Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks
- LoRA: Low-Rank Adaptation of Large Language Models
- WISE: Rethinking the Knowledge Memory for Lifelong Model Editing of Large Language Models
- RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models
- Editing as Unlearning: Are Knowledge Editing Methods Strong Baselines for Large Language Model Unlearning?
- Do LLMs Really Forget? Evaluating Unlearning with Knowledge Correlation and Confidence Awareness
- Decoupled Weight Decay Regularization
- Large Language Model Unlearning
- TOFU: A Task of Fictitious Unlearning for LLMs
- Locating and Editing Factual Associations in GPT
- A Comprehensive Study of Knowledge Editing for Large Language Models
- Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning
Related papers
- Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
- Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
- Subliminal Steering: Stronger Encoding of Hidden Signals
- MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
- The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
- Untangling the Mechanisms of Misleading Context in Medical Question Answering