On the Recoverability of Private Information Unlearning in Large Language Models
cs.LG, cs.CL
Submitted: 2026-08-30
Updated: 2026-08-30
Code: https://github.com/rzTian/LLM-Unlearning-Recovery
Project page: https://brunstud.github.io/fpi-unlearning
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Language Models are Few-Shot Learners
- Do Unlearning Methods Remove Information from Language Model Weights?
- Who's Harry Potter? Approximate Unlearning in LLMs
- LoRA: Low-Rank Adaptation of Large Language Models
- Reversing the Forget-Retain Objectives: An Efficient LLM Unlearning Framework from Logit Difference
- RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models
- Scaling Laws for Neural Language Models
- Large Language Model Unlearning via Embedding-Corrupted Prompts
- Eight Methods to Evaluate Robust Unlearning in LLMs
- TOFU: A Task of Fictitious Unlearning for LLMs
- GPT-4 Technical Report
- Direct Preference Optimization: Your Language Model is Secretly a Reward Model
- MUSE: Machine Unlearning Six-Way Evaluation for Language Models
- Evaluating Copyright Takedown Methods for Language Models
- Qwen3 Technical Report
- Large Language Model Unlearning
- Counterfactual Memorization in Neural Language Models
- Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning
- Catastrophic Failure of LLM Unlearning via Quantization
- Universal and Transferable Adversarial Attacks on Aligned 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