This repository is a curated list of research papers, surveys, frameworks, and blog posts focused on machine unlearning in Large Language Models (LLMs). It serves as a comprehensive resource for researchers and practitioners in the field of AI safety and privacy, aiming to track the latest advancements and open challenges in selectively removing knowledge from LLMs.

How It Works

The repository functions as a dynamic bibliography, organized by year and category (Papers, Surveys, Frameworks, Blog Posts). It aims to provide a centralized and up-to-date collection of academic and practical resources related to LLM unlearning, facilitating easier access to relevant research for the community.

Quick Start & Requirements

This repository is a curated list and does not require installation or execution. It serves as a reference guide.

Highlighted Details

• Contains 184 papers, 13 surveys, 1 framework, and 2 blog posts as of the last update.
• Papers are categorized by year, starting from 2021, with a significant number of entries for 2024 and 2025.
• Includes a dedicated section for surveys and position papers, offering broader overviews of the field.
• Lists frameworks and blog posts to cover different aspects of LLM unlearning research and discussion.

Maintenance & Community

The repository encourages community contributions through issues and pull requests for adding new papers or correcting existing information.

Licensing & Compatibility

The repository itself is not software and thus not subject to software licensing. The linked papers and resources are governed by their respective licenses.

Limitations & Caveats

The content is dependent on community contributions for updates and accuracy. The list may not be exhaustive, and the inclusion of a paper does not constitute an endorsement of its methodology or findings.