Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Action Level Prediction on Abg-CoQA (OOD)
Loading...
93.44
Ambiguous Acc
ProMed(S#1)+DPO
58.8288
67.8144
76.8
85.7856
Aug 19, 2025
Ambiguous Acc
Non-Ambiguous Acc
Macro Acc
Updated 1mo ago
Evaluation Results
Method
Method
Links
Ambiguous Acc
Non-Ambiguous Acc
Macro Acc
ProMed(S#1)+DPO
Training=CMB-trained,...
2025.08
93.44
9.11
51.28
ProMed(S#1+2)
Training=CMB-trained,...
2025.08
79.51
34.3
56.91
ProMed(S#1)+GRPO
Training=CMB-trained,...
2025.08
77.24
30.93
54.08
Vanilla
Training=CMB-trained,...
2025.08
60.16
48.11
54.15
Feedback
Search any
task
Search any
task