Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Continual Learning on SelfRC, TweetQA, and SST sequence SQuAD format (test)
Loading...
82.8
Average EM
Multitasked
37.144
48.997
60.85
72.703
Dec 17, 2025
Average EM
Updated 4d ago
Evaluation Results
Method
Method
Links
Average EM
Multitasked
Evaluation Protocol=Up...
2025.12
82.8
PPSEBM
Sampling Ratio=0.2, Ge...
2025.12
80.9
LSEBMCL
Sampling Ratio=0.2, Ge...
2025.12
80.2
PPSEBM
Sampling Ratio=0.05, G...
2025.12
79.8
LSEBMCL
Sampling Ratio=0.05, G...
2025.12
78.9
RVAE-LAMOL
Sampling Ratio=0.2, Ge...
2025.12
77.2
LAMOL
Sampling Ratio=0.2, Ge...
2025.12
76.3
RVAE-LAMOL
Sampling Ratio=0.05, G...
2025.12
76.1
LAMOL
Sampling Ratio=0.05, G...
2025.12
76
PPSEBM
Sampling Ratio=0, Gene...
2025.12
57.6
LSEBMCL
Sampling Ratio=0, Gene...
2025.12
55.4
GEM
Task Order=SelfRC -> T...
2025.12
50
Fine-tuned
Task Order=SelfRC -> T...
2025.12
49.8
EWC
Task Order=SelfRC -> T...
2025.12
49
LAMOL
Sampling Ratio=0, Gene...
2025.12
45.2
MAS
Task Order=SelfRC -> T...
2025.12
38.9
Feedback
Search any
task
Search any
task