Share your thoughts, 1 month free Claude Pro on us
See more
Home
/
Benchmarks
Off-policy evaluation on HotpotQA (DPO)
Loading...
0.9
Rho
ADWM
-0.036
0.207
0.45
0.693
Jun 4, 2026
Rho
95% CI
P-Value
Updated 1mo ago
Evaluation Results
Method
Method
Links
Rho
95% CI
P-Value
ADWM
n=5
2026.06
0.9
0.11
0.037
DR
n=5
2026.06
0.9
-
-
IS
n=5
2026.06
0.9
-
-
WIS
n=5
2026.06
0.9
-
-
FQE
n=5
2026.06
0.1
-
-
DM
n=5
2026.06
0
-
-
Feedback
Search any
task
Search any
task