Exposing the Illusion of Erasure in Knowledge Editing for LLMs
cs.LG, cs.AI, cs.CR
Submitted: 2026-06-22
Updated: 2026-11-05
Code: https://github.com/kingoflolz/mesh-transformer-jax
Terminology
Sources
- Constitutional AI: Harmlessness from AI Feedback
- Machine Unlearning
- Language Models are Few-Shot Learners
- Editing Factual Knowledge in Language Models
- Extracting Training Data from Large Language Models
- Quantifying Memorization Across Neural Language Models
- Knowledge Neurons in Pretrained Transformers
- Sharpness-Aware Minimization for Efficiently Improving Generalization
- Inverting Gradients -- How easy is it to break privacy in federated learning?
- An Investigation into Neural Net Optimization via Hessian Eigenvalue Density
- The Llama 3 Herd of Models
- Mechanistic Unlearning: Robust Knowledge Unlearning and Editing via Mechanistic Localization
- Does Localization Inform Editing? Surprising Differences in Causality-Based Localization vs. Knowledge Editing in Language Models
- Can Knowledge Editing Really Correct Hallucinations?
- Zero-Shot Relation Extraction via Reading Comprehension
- Visualizing the Loss Landscape of Neural Nets
- TruthfulQA: Measuring How Models Mimic Human Falsehoods
- Locating and Editing Factual Associations in GPT
- Mass-Editing Memory in a Transformer
- Fast Model Editing at Scale
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