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

Awesome Machine Unlearning (A Survey of Machine Unlearning)

A resource repository for machine unlearning in large language models

[NeurIPS D&B '25] The one-stop repository for LLM unlearning

[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

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

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

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.

[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

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

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

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

[ACL 2025] Knowledge Unlearning for Large Language Models

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

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

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

Code for implementation of Unlearning Scanner Bias for MRI Harmonisation

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".