Machine Unlearning on ToFU Neighbouring Knowledge (NEK) (one author)
78ROUGE-LAttention-Shifting
Evaluation results
| Method | Links | ||
|---|---|---|---|
| Attention-ShiftingTraining Mode=Adapters only, Data Balance=Remaining data equal to TUD2025.10 | 78 | 79 | |
| IHL + KLTraining Mode=Adapters only, Data Balance=Remaining data equal to TUD2025.10 | 70 | 73 | |
| IHL + CETraining Mode=Adapters only, Data Balance=Remaining data equal to TUD2025.10 | 67 | 67 | |
| GA + CETraining Mode=Adapters only, Data Balance=Remaining data equal to TUD2025.10 | 62 | 61 | |
| IHLTraining Mode=Adapters only, Data Balance=Remaining data equal to TUD2025.10 | 45 | 46 | |
| ULDTraining Mode=Adapters only, Data Balance=Remaining data equal to TUD2025.10 | 41 | 43 | |
| NPO + KLTraining Mode=Adapters only, Data Balance=Remaining data equal to TUD2025.10 | 40 | 41 | |
| NPO + CETraining Mode=Adapters only, Data Balance=Remaining data equal to TUD2025.10 | 39 | 40 | |
| GA + KLTraining Mode=Adapters only, Data Balance=Remaining data equal to TUD2025.10 | 36 | 32 | |
| GATraining Mode=Adapters only, Data Balance=Remaining data equal to TUD2025.10 | 34 | 39 | |
| NPOTraining Mode=Adapters only, Data Balance=Remaining data equal to TUD2025.10 | 25 | 26 |