Requirements
To claim this bounty, we expect you to
- reimplement Lee et al.’s methodology from scratch to ensure they made no implementation errors;
- show the effectiveness of Unlearning-and-Distill and Unlearn-Noise-Distill-on-Outputs relative to baseline methods; and
- use a model not included in the original result.
If you do not meet these requirements, still consider submitting a proposal, but we may need to lower the bounty.
If you’d like a higher bounty, you could try
- using different retain/forget corpora; or
- using a different unlearning method.
Contact us if you have any questions.
Submit a Proposal
Use our submission form to send us your proposal. See the instructions for more details on the proposal and preregistration process.