News for hackers. Stuff that matters.

A comment on An embarrassingly simple approach to recover unlearned knowledge for LLMs.

Re:An embarrassingly simple approach to recover unlearned kn... by yalogin on Monday November 04, 2024 @04:14AM (#42039846)
This is the first time I am learning about model unlearning. I hope someone can answer this for me - how does federated learning ensure that model unlearning is not happening?
[ Parent | on HN ]
Re:An embarrassingly simple approach to recover unlearned kn... by Writingdorky on Monday November 04, 2024 @04:19AM (#42039865)
You prope the trained model, delete/kill the weights and than you are done.

On federated learning, you just make sure to keep this mechanism in the right stage of your pipeline

[ Parent | on HN ]