Our new X account is live! Follow @wizwand_team for updates
Home
/
Benchmarks
Sentiment and topic classification on Subj (test)
Loading...
89.3
Macro-F1
IDAICL
35.844
49.722
63.6
77.478
May 28, 2023
Aug 2, 2023
Oct 7, 2023
Dec 12, 2023
Feb 16, 2024
Apr 22, 2024
Jun 27, 2024
Macro-F1
Updated 4d ago
Evaluation Results
Method
Method
Links
Macro-F1
IDAICL
PLM=LLaMA 33B, m=4
2024.06
89.3
PROCA
PLM=LLaMA 33B, m=4
2024.06
88.3
IDAICL
PLM=LLaMA 13B, m=4
2024.06
87.8
Vanilla ICL
PLM=LLaMA 33B, m=4
2024.06
85.1
PROCA
PLM=LLaMA 13B, m=4
2024.06
84.8
D-ConCa
PLM=LLaMA 13B, m=4
2024.06
82.9
ConCa
PLM=LLaMA 13B, m=4
2024.06
79.6
D-ConCa
PLM=LLaMA 33B, m=4
2024.06
76.4
ConCa
PLM=LLaMA 33B, m=4
2024.06
74.6
Vanilla ICL
PLM=LLaMA 13B, m=4
2024.06
72.9
RoBERTa-large (Context Calibration)
Model=RoBERTa-large, S...
2023.05
51.6
RoBERTa-large (Domain-context Calibration)
Model=RoBERTa-large, S...
2023.05
44.3
RoBERTa-large (Original)
Model=RoBERTa-large, S...
2023.05
37.9
Feedback
Search any
task
Search any
task