awesome-llm-unlearning

Why we included this project

Machine unlearning is one of those areas where the research moves faster than most teams can track, and this index does the tracking for you. It collects papers, surveys, benchmarks, and a few frameworks on removing knowledge from large language models, organized by year and by type so you can see how the field has shifted and which evaluation benchmarks keep showing up. The maintainer takes pull requests and corrections, so the list tracks new arXiv work without much lag. It is a reading map, not software: use it to find the papers and datasets worth evaluating, not something to deploy.