Views
No views yet
| Field | Value |
|---|---|
| Unlearning method | RMU |
| Base model | meta-llama/Llama-3.1-8B-Instruct |
| Target concept | Uranium |
| Checkpoint type | Full Model Weights |
| Rank / seed | 200 / 42 |
| Train eval protocol | mc |
unlearned_checkpoints.json):| Parameter | Value |
|---|---|
alpha | 100 |
delta_embed | 0 |
k_features_embed | 0 |
layer_id | 9 |
layer_ids | 7,8,9 |
lr | 0.0001 |
n_tokens_edited | 0 |
param_ids | 6 |
setting_name | S2_lid9_L789 |
steering | 30 |
| Metric | Train (after unlearning) | Test (after unlearning) |
|---|---|---|
| Efficacy | 1 | 1 |
| Specificity | 0.795 | 0.866 |
| Harmonic mean | 0.886 | 0.928 |
| Relearning QA (MC) | — | 0.38 |
evaluation/score_comparison.csv:| Metric | Baseline (train) | After unlearn (train) | Baseline (test) | After unlearn (test) |
|---|---|---|---|---|
| QA accuracy | 0.76 | 0.16 | 0.8 | 0.2 |
| QA fraction | 1 | 0 | 1 | 0 |
| SimDom accuracy | 0.72 | 0.56 | 0.68 | 0.6 |
| SimDom fraction | 1 | 0.66 | 1 | 0.814 |
| MMLU accuracy | 0.62 | 0.64 | 0.65 | 0.62 |
| MMLU fraction | 1 | 1 | 1 | 0.925 |
| File | Description |
|---|---|
unlearned_checkpoints.json | Checkpoint metadata & hyperparameters |
evaluation/evaluation_summary.json | Full evaluation payload (train/test/relearning) |
evaluation/score_comparison.csv | Baseline vs. unlearned comparison table |