Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Counterfactual Knowledge Editing on CounterFact (150 random samples)
Loading...
100
Efficacy Score
FT
16.072
37.861
59.65
81.439
Jun 15, 2023
Efficacy Score
Paraphrase Score
Neighborhood Score +
Score *
Updated 4d ago
Evaluation Results
Method
Method
Links
Efficacy Score
Paraphrase Score
Neighborhood Score +
Score *
FT
Base Model=GPT2-XL, Ed...
2023.06
100
92
10.5
25.8
ROME
Base Model=GPT2-XL
2023.06
100
95.3
13.8
32.3
FT + L
Base Model=GPT2-XL, Ed...
2023.06
99.3
42.7
40.9
51.8
Distillation
Base Model=GPT2-XL
2023.06
79.3
68
22.8
42.2
Base
Base Model=GPT2-XL, Up...
2023.06
19.3
23.7
53.7
26.6
Feedback
Search any
task
Search any
task