[ACL 2024] An Easy-to-use Knowledge Editing Framework for LLMs.

natural-language-processing tool efficient artificial-intelligence llama gpt baichuan mmedit unlearning trustworthy-ai large-language-models chatgpt model-editing knowledge-editing knowlm easyedit safeedit knowedit cknowedit easyedit2

• Updated Nov 7, 2026
• Jupyter Notebook

Awesome Machine Unlearning (A Survey of Machine Unlearning)

data-privacy gdpr right-to-be-forgotten machine-unlearning continual-learning forgetting data-deletion unlearning membership-inference data-removal model-certification federated-unlearning recommendation-unlearning few-shot-unlearning unlearning-verification feature-injection deep-unlearning llm-unlearning

• Updated Aug 13, 2026
• Jupyter Notebook

A resource repository for machine unlearning in large language models

nlp machine-learning awesome privacy evaluation alignment awesome-list ai-safety right-to-be-forgotten machine-unlearning paper-list responsible-ai unlearning llm model-editing large-language-model llm-safety llm-unlearning selective-forgetting knowledge-erasure

• Updated Oct 6, 2026

[NeurIPS 2025] The one-stop repository for LLM unlearning

open-source benchmarks right-to-be-forgotten privacy-protection unlearning membership-inference-attacks membership-inference llms llm-privacy llm-unlearning llm-evaluation-metrics

• Updated Nov 11, 2026
• Python

[ICLR24 (Spotlight)] "SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation" by Chongyu Fan*, Jiancheng Liu*, Yihua Zhang, Eric Wong, Dennis Wei, Sijia Liu

generative-model data-privacy diffusion machine-unlearning forgetting diffusion-models data-deletion membership-inference-attack unlearning membership-inference data-removal

• Updated Feb 28, 2026
• Python

RWKU: Benchmarking Real-World Knowledge Unlearning for Large Language Models. NeurIPS 2024

benchmark natural-language-processing right-to-be-forgotten evaluation-framework privacy-protection adversarial-attacks forgetting membership-inference-attack unlearning large-language-models

• Updated Sep 30, 2024
• Python

A Visual Analytics System for Comparative Evaluation of Machine Unlearning Methods (TVCG 2026)

visualization benchmark evaluation visual-analytics machine-unlearning unlearning

• Updated Sep 12, 2026
• TypeScript

[NeurIPS23 (Spotlight)] "Model Sparsity Can Simplify Machine Unlearning" by Jinghan Jia*, Jiancheng Liu*, Parikshit Ram, Yuguang Yao, Gaowen Liu, Yang Liu, Pranay Sharma, Sijia Liu

data-privacy machine-unlearning forgetting data-deletion membership-inference-attack unlearning membership-inference data-removal

• Updated Jun 28, 2026
• Python

The official implementation of ECCV'24 paper "To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Now". This work introduces one fast and effective attack method to evaluate the harmful-content generation ability of safety-driven unlearned diffusion models.

evaluation-framework robustness adversarial-attacks unlearning stable-diffusion attack-unlearned-diffusion-model

• Updated Feb 28, 2025
• Python

data-privacy uncertainty-quantification machine-unlearning conformal-prediction unlearning

• Updated Oct 20, 2026
• Python

Practical Continual Forgetting for Pre-trained Vision Models (CVPR 2024; T-PAMI 2026)

editing machine-unlearning continual-learning forgetting unlearning model-editing face-transformer casia-webface continual-forgetting

• Updated Oct 25, 2026
• Python

[ACL 2024] Code and data for "Machine Unlearning of Pre-trained Large Language Models"

data-privacy machine-unlearning copyright-protection unlearning llm llm-unlearning

• Updated Sep 30, 2024
• Python

data-privacy machine-unlearning unlearning

• Updated May 1, 2026
• Python

Official implementation of NeurIPS'24 paper "Defensive Unlearning with Adversarial Training for Robust Concept Erasure in Diffusion Models". This work adversarially unlearns the text encoder to enhance the robustness of unlearned DMs against adversarial prompt attacks and achieves a better balance between unlearning performance and image generation

robust-optimization adversarial-machine-learning unlearning stable-diffusion unlearned-diffusion-model

• Updated Nov 4, 2024
• Jupyter Notebook

[EMNLP 2024] To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models

benchmark natural-language-processing localization artificial-intelligence dataset unlearning large-language-models model-editing knowledge-editing knowledge-unlearning knowundo memflex

• Updated Jan 23, 2025
• Python

[ACL 2025] Knowledge Unlearning for Large Language Models

natural-language-processing privacy artificial-intelligence copyright machine-unlearning unlearning large-language-models knowledge-editing knowledge-unlearning semeval-2025

• Updated Sep 18, 2025
• Python

[NeurIPS 2024] Large Language Model Unlearning via Embedding-Corrupted Prompts

alignment machine-unlearning unlearning large-language-models llm-unlearning

• Updated Sep 26, 2024
• Python

[EMNLP 2025 Main] ConceptVectors Benchmark and Code for the paper "Intrinsic Evaluation of Unlearning Using Parametric Knowledge Traces"

natural-language-processing interpretability unlearning large-language-models

• Updated Aug 20, 2025
• Jupyter Notebook

Code for implementation of Unlearning Scanner Bias for MRI Harmonisation

domain-adaptation harmonisation unlearning

• Updated Jun 21, 2021
• Python

machine-unlearning unlearning llm chatgpt llm-unlearning

• Updated Dec 18, 2025