Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Model Editing on KAMEL multi-token targets (N=3)
Loading...
76
Efficacy
MEMIT + Correction
31.28
42.89
54.5
66.11
Jun 2, 2026
Efficacy
Generality
Updated 1mo ago
Evaluation Results
Method
Method
Links
Efficacy
Generality
MEMIT + Correction
Model=LLaDA
2026.06
76
36
MEMIT + Correction
Model=Dream
2026.06
59
56
MEMIT (MDM adaptation)
Model=Dream
2026.06
46
32
MEMIT (MDM adaptation)
Model=LLaDA
2026.06
33
20
Feedback
Search any
task
Search any
task