unlearning 开源项目推荐（81 个）

zjunlp /EasyEdit

[ACL 2024]一个易于使用的LLM知识编辑框架。

tamlhp /awesome-machine-unlearning

Awesome Machine Unlearning (A Survey of Machine Unlearning)

chrisliu298 /awesome-llm-unlearning

A resource repository for machine unlearning in large language models

locuslab /open-unlearning

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

OPTML-Group /Unlearn-Saliency

[ICLR24（聚焦）]《SalUn：通过基于梯度的权重显著性在图像分类与生成中赋能机器学习》，作者：Chongyu Fan*、Jiancheng Liu*、Zhang Yihua、Eric Wong、Dennis Wei、Sijia Liu

jinzhuoran /RWKU

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

gnueaj /Machine-Unlearning-Comparator

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

OPTML-Group /Unlearn-Sparse

[NeurIPS23（聚焦）]《模型稀疏可以简化机器学习去学习》 作者：贾景汉*、刘建成*、帕里克希特·拉姆、姚玉光、刘高文、刘杨、普拉奈·夏尔马、刘思嘉

OPTML-Group /Diffusion-MU-Attack

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.

TIML-Group /Conformal-Prediction-Unlearning

该项目在 GitHub 上没有填写描述

bjzhb666 /GS-LoRA

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

yaojin17 /Unlearning_LLM

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

TIML-Group /Mode-Connectivity-Unlearning

该项目在 GitHub 上没有填写描述

OPTML-Group /AdvUnlearn

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

zjunlp /KnowUnDo

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

zjunlp /unlearn

[ACL 2025] Knowledge Unlearning for Large Language Models

chrisliu298 /llm-unlearn-eco

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

yihuaihong /ConceptVectors

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

nkdinsdale /Unlearning_for_MRI_harmonisation

Code for implementation of Unlearning Scanner Bias for MRI Harmonisation

KID-22 /LLM-Unlearning-Paper-List

该项目在 GitHub 上没有填写描述