## Expected File Format

We expect your submitted file to be in the CSV format containing the following columns:
- `name`: Name of the evaluated unlearning method. Must be unique for each row.
- `verbmem_f`, `privleak`, `knowmem_f`, `knowmem_r`: Evaluation scores.

Following the instructions for evaluation in our [GitHub Repository](https://github.com/jaechan-repo/muse_bench) yields an output file precisely of this format.

## Quick Links

- [Website](https://muse-bench.github.io): Landing page for MUSE.
- [arXiv Paper](): Detailed information about MUSE and analysis on the baseline unlearning methods.
- [GitHub Repository](https://github.com/jaechan-repo/muse_bench): Evaluation scripts, implementations of the baseline unlearning methods.
- [News Dataset](https://huggingface.co./datasets/muse-bench/MUSE-News), [Books Dataset](https://huggingface.co./datasets/muse-bench/MUSE-Books): Two evaluation corpora used by MUSE.
- [Leaderboard](https://huggingface.co./spaces/muse-bench/muse_leaderboard) (You are here): Current rankings of unlearning algorithms for MUSE.
- [Summary on Twitter](): A concise summary and key takeaways from the project.