Unlearning Benchmark

Creator
Creator
Seonglae ChoSeonglae Cho
Created
Created
2025 Jul 21 11:24
Editor
Edited
Edited
2025 Jul 21 11:39
Refs
Refs
Unlearning benchmark (including TOFU) has one of the biggest risks, which is "improving scores by simply breaking the model". In other words, if you just make the model brittle so that it can't say anything about the forget set, the Forget Accuracy increases, but this is far from truly meaningful selective forgetting. That's why Retain Accuracy is also essential, and a combined score of forget and retain is used.
Unlearning Benchmarks
 
 
 
 

Unlearning evaluation methods

 

Recommendations