awesome-machine-unlearning
Awesome Machine Unlearning (A Survey of Machine Unlearning)
- 977
- Jupyter Notebook
- MIT
- 3 mo ago
Awesome Machine Unlearning (A Survey of Machine Unlearning)
A resource repository for machine unlearning in large language models
[NeurIPS25] Official repo for "Simplicity Prevails: Rethinking Negative Preference Optimization for LLM Unlearning"
[ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"
[NeurIPS 2024] Large Language Model Unlearning via Embedding-Corrupted Prompts
FALCON: Fine-grained Activation Manipulation for LLM Unlearning (NeurIPS 2025)
ICLR 2026: Implementation of our unlearning method "Partial Model Collapse" introduced in: "Model Collapse Is Not a Bug but a Feature in Machine Unlearning for LLMs".
[EMNLP 2026 (Oral)] Measuring the Depth of LLM Unlearning via Activation Patching
The LLM Unlearning repository is an open-source project dedicated to the concept of unlearning in Large Language Models (LLMs). It aims to address concerns about data privacy and ethical AI by exploring and implementing unlearning techniques that allow models to forget unwanted or sensitive data. This ensures that AI models comply with privacy.
ICLR 2025 Oral: Implementation of the probabilistic evaluation framework introduced in the paper: "A Probabilistic Perspective on Unlearning and Alignment for Large Language Models" accepted at ICLR 2025 (Oral).
Usenix Security’25: Measuring Sample-level Unlearning Completeness
AAAI-25: On Effects of Steering Latent Representation for Large Language Model Unlearning
A continuously-updated catalog of machine unlearning papers with live citation counts.