Awesome LLM Unlearning
A curated, actively updated list of papers, surveys, frameworks and posts about machine unlearning in large language models, that is, removing specific knowledge or training data from a model after the fact.
Awesome LLM Unlearning is a reference collection for the machine unlearning literature as it applies to large language models: making a model forget particular facts, training examples or capabilities without retraining it from scratch. As of its last update it lists over 600 papers plus surveys, position papers, frameworks and blog posts, organized by year from 2021 to 2026.
Entries are grouped into papers, surveys and position papers, frameworks, and blog posts, each with authors, date, venue and a code link where one exists, and the maintainer accepts corrections and additions through issues or pull requests.