🧠 OpenUnlearning Hub: A Collection of Trained/Unlearned LLMs

Welcome to the OpenUnlearning Hub, a central repository of models trained and unlearned using the OpenUnlearning framework — a standardized toolkit for benchmarking and accelerating machine unlearning in large language models (LLMs).

OpenUnlearning is a unified and extensible framework for:

• Evaluating unlearning methods and metrics
• Comparing the efficiency of forgetting algorithms
• Providing a common benchmark to accelerate research in LLM unlearning

Read our paper for the full details: 📄 arXiv:2506.12618

📣 Citation

If you use our models or code in your research or applications, please cite:

@article{openunlearning2025,
  title={{OpenUnlearning}: Accelerating {LLM} Unlearning via Unified Benchmarking of Methods and Metrics},
  author={Dorna, Vineeth and Mekala, Anmol and Zhao, Wenlong and McCallum, Andrew and Lipton, Zachary C and Kolter, J Zico and Maini, Pratyush},
  journal={arXiv preprint arXiv:2506.12618},
  year={2025},
}