Skip to content

Explore: machine unlearning (right to be forgotten) #34

Description

@NotYuSheng

Remove a specific person or conversation from an already-trained model on request — the consent theme made concrete.

Directions: unlearning methods (gradient ascent, SISA, adapter ablation); verify the data is gone via extraction tests. Part of the exploratory roadmap.

Metadata

Metadata

Assignees

No one assigned

    Labels

    explorationExploratory research direction

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions